update Scintilla to v3.3.4 [e074c3]

48 files changed, 5006 insertions, 858 deletions

diff --git a/scintilla/Scintilla.vcxproj b/scintilla/Scintilla.vcxproj
index eeca2ea..51bd579 100644
--- a/scintilla/Scintilla.vcxproj
+++ b/scintilla/Scintilla.vcxproj
@@ -160,6 +160,7 @@
     <ClCompile Include="lexers\LexVB.cxx" />
     <ClCompile Include="lexers\LexYAML.cxx" />
     <ClCompile Include="lexlib\Accessor.cxx" />
+    <ClCompile Include="lexlib\CharacterCategory.cxx" />
     <ClCompile Include="lexlib\CharacterSet.cxx" />
     <ClCompile Include="lexlib\LexerBase.cxx" />
     <ClCompile Include="lexlib\LexerModule.cxx" />
@@ -170,6 +171,8 @@
     <ClCompile Include="lexlib\WordList.cxx" />
     <ClCompile Include="src\AutoComplete.cxx" />
     <ClCompile Include="src\CallTip.cxx" />
+    <ClCompile Include="src\CaseConvert.cxx" />
+    <ClCompile Include="src\CaseFolder.cxx" />
     <ClCompile Include="src\Catalogue.cxx" />
     <ClCompile Include="src\CellBuffer.cxx" />
     <ClCompile Include="src\CharClassify.cxx" />
@@ -200,6 +203,7 @@
     <ClInclude Include="include\SciLexer.h" />
     <ClInclude Include="include\Scintilla.h" />
     <ClInclude Include="lexlib\Accessor.h" />
+    <ClInclude Include="lexlib\CharacterCategory.h" />
     <ClInclude Include="lexlib\CharacterSet.h" />
     <ClInclude Include="lexlib\LexAccessor.h" />
     <ClInclude Include="lexlib\LexerBase.h" />
@@ -214,6 +218,8 @@
     <ClInclude Include="lexlib\WordList.h" />
     <ClInclude Include="src\AutoComplete.h" />
     <ClInclude Include="src\CallTip.h" />
+    <ClInclude Include="src\CaseConvert.h" />
+    <ClInclude Include="src\CaseFolder.h" />
     <ClInclude Include="src\Catalogue.h" />
     <ClInclude Include="src\CellBuffer.h" />
     <ClInclude Include="src\CharClassify.h" />
diff --git a/scintilla/Scintilla.vcxproj.filters b/scintilla/Scintilla.vcxproj.filters
index 8b57396..a22b24b 100644
--- a/scintilla/Scintilla.vcxproj.filters
+++ b/scintilla/Scintilla.vcxproj.filters
@@ -96,6 +96,9 @@
     <ClCompile Include="lexlib\Accessor.cxx">
       <Filter>lexlib</Filter>
     </ClCompile>
+    <ClCompile Include="lexlib\CharacterCategory.cxx">
+      <Filter>lexlib</Filter>
+    </ClCompile>
     <ClCompile Include="lexlib\CharacterSet.cxx">
       <Filter>lexlib</Filter>
     </ClCompile>
@@ -126,6 +129,12 @@
     <ClCompile Include="src\CallTip.cxx">
       <Filter>src</Filter>
     </ClCompile>
+    <ClCompile Include="src\CaseConvert.cxx">
+      <Filter>src</Filter>
+    </ClCompile>
+    <ClCompile Include="src\CaseFolder.cxx">
+      <Filter>src</Filter>
+    </ClCompile>
     <ClCompile Include="src\Catalogue.cxx">
       <Filter>src</Filter>
     </ClCompile>
@@ -212,6 +221,9 @@
     <ClInclude Include="lexlib\Accessor.h">
       <Filter>lexlib</Filter>
     </ClInclude>
+    <ClInclude Include="lexlib\CharacterCategory.h">
+      <Filter>lexlib</Filter>
+    </ClInclude>
     <ClInclude Include="lexlib\CharacterSet.h">
       <Filter>lexlib</Filter>
     </ClInclude>
@@ -254,6 +266,12 @@
     <ClInclude Include="src\CallTip.h">
       <Filter>src</Filter>
     </ClInclude>
+    <ClInclude Include="src\CaseConvert.h">
+      <Filter>src</Filter>
+    </ClInclude>
+    <ClInclude Include="src\CaseFolder.h">
+      <Filter>src</Filter>
+    </ClInclude>
     <ClInclude Include="src\Catalogue.h">
       <Filter>src</Filter>
     </ClInclude>
diff --git a/scintilla/Scintilla_VS2010.vcxproj b/scintilla/Scintilla_VS2010.vcxproj
index ae42593..713f70b 100644
--- a/scintilla/Scintilla_VS2010.vcxproj
+++ b/scintilla/Scintilla_VS2010.vcxproj
@@ -155,6 +155,7 @@
     <ClCompile Include="lexers\LexVB.cxx" />
     <ClCompile Include="lexers\LexYAML.cxx" />
     <ClCompile Include="lexlib\Accessor.cxx" />
+    <ClCompile Include="lexlib\CharacterCategory.cxx" />
     <ClCompile Include="lexlib\CharacterSet.cxx" />
     <ClCompile Include="lexlib\LexerBase.cxx" />
     <ClCompile Include="lexlib\LexerModule.cxx" />
@@ -165,6 +166,8 @@
     <ClCompile Include="lexlib\WordList.cxx" />
     <ClCompile Include="src\AutoComplete.cxx" />
     <ClCompile Include="src\CallTip.cxx" />
+    <ClCompile Include="src\CaseConvert.cxx" />
+    <ClCompile Include="src\CaseFolder.cxx" />
     <ClCompile Include="src\Catalogue.cxx" />
     <ClCompile Include="src\CellBuffer.cxx" />
     <ClCompile Include="src\CharClassify.cxx" />
@@ -195,6 +198,7 @@
     <ClInclude Include="include\SciLexer.h" />
     <ClInclude Include="include\Scintilla.h" />
     <ClInclude Include="lexlib\Accessor.h" />
+    <ClInclude Include="lexlib\CharacterCategory.h" />
     <ClInclude Include="lexlib\CharacterSet.h" />
     <ClInclude Include="lexlib\LexAccessor.h" />
     <ClInclude Include="lexlib\LexerBase.h" />
@@ -209,6 +213,8 @@
     <ClInclude Include="lexlib\WordList.h" />
     <ClInclude Include="src\AutoComplete.h" />
     <ClInclude Include="src\CallTip.h" />
+    <ClInclude Include="src\CaseConvert.h" />
+    <ClInclude Include="src\CaseFolder.h" />
     <ClInclude Include="src\Catalogue.h" />
     <ClInclude Include="src\CellBuffer.h" />
     <ClInclude Include="src\CharClassify.h" />
diff --git a/scintilla/Scintilla_VS2010.vcxproj.filters b/scintilla/Scintilla_VS2010.vcxproj.filters
index 8b57396..a22b24b 100644
--- a/scintilla/Scintilla_VS2010.vcxproj.filters
+++ b/scintilla/Scintilla_VS2010.vcxproj.filters
@@ -96,6 +96,9 @@
     <ClCompile Include="lexlib\Accessor.cxx">
       <Filter>lexlib</Filter>
     </ClCompile>
+    <ClCompile Include="lexlib\CharacterCategory.cxx">
+      <Filter>lexlib</Filter>
+    </ClCompile>
     <ClCompile Include="lexlib\CharacterSet.cxx">
       <Filter>lexlib</Filter>
     </ClCompile>
@@ -126,6 +129,12 @@
     <ClCompile Include="src\CallTip.cxx">
       <Filter>src</Filter>
     </ClCompile>
+    <ClCompile Include="src\CaseConvert.cxx">
+      <Filter>src</Filter>
+    </ClCompile>
+    <ClCompile Include="src\CaseFolder.cxx">
+      <Filter>src</Filter>
+    </ClCompile>
     <ClCompile Include="src\Catalogue.cxx">
       <Filter>src</Filter>
     </ClCompile>
@@ -212,6 +221,9 @@
     <ClInclude Include="lexlib\Accessor.h">
       <Filter>lexlib</Filter>
     </ClInclude>
+    <ClInclude Include="lexlib\CharacterCategory.h">
+      <Filter>lexlib</Filter>
+    </ClInclude>
     <ClInclude Include="lexlib\CharacterSet.h">
       <Filter>lexlib</Filter>
     </ClInclude>
@@ -254,6 +266,12 @@
     <ClInclude Include="src\CallTip.h">
       <Filter>src</Filter>
     </ClInclude>
+    <ClInclude Include="src\CaseConvert.h">
+      <Filter>src</Filter>
+    </ClInclude>
+    <ClInclude Include="src\CaseFolder.h">
+      <Filter>src</Filter>
+    </ClInclude>
     <ClInclude Include="src\Catalogue.h">
       <Filter>src</Filter>
     </ClInclude>
diff --git a/scintilla/Scintilla_icl13.vcxproj b/scintilla/Scintilla_icl13.vcxproj
index 5c1fe21..056f98d 100644
--- a/scintilla/Scintilla_icl13.vcxproj
+++ b/scintilla/Scintilla_icl13.vcxproj
@@ -180,6 +180,7 @@
     <ClCompile Include="lexers\LexVB.cxx" />
     <ClCompile Include="lexers\LexYAML.cxx" />
     <ClCompile Include="lexlib\Accessor.cxx" />
+    <ClCompile Include="lexlib\CharacterCategory.cxx" />
     <ClCompile Include="lexlib\CharacterSet.cxx" />
     <ClCompile Include="lexlib\LexerBase.cxx" />
     <ClCompile Include="lexlib\LexerModule.cxx" />
@@ -190,6 +191,8 @@
     <ClCompile Include="lexlib\WordList.cxx" />
     <ClCompile Include="src\AutoComplete.cxx" />
     <ClCompile Include="src\CallTip.cxx" />
+    <ClCompile Include="src\CaseConvert.cxx" />
+    <ClCompile Include="src\CaseFolder.cxx" />
     <ClCompile Include="src\Catalogue.cxx" />
     <ClCompile Include="src\CellBuffer.cxx" />
     <ClCompile Include="src\CharClassify.cxx" />
@@ -220,6 +223,7 @@
     <ClInclude Include="include\SciLexer.h" />
     <ClInclude Include="include\Scintilla.h" />
     <ClInclude Include="lexlib\Accessor.h" />
+    <ClInclude Include="lexlib\CharacterCategory.h" />
     <ClInclude Include="lexlib\CharacterSet.h" />
     <ClInclude Include="lexlib\LexAccessor.h" />
     <ClInclude Include="lexlib\LexerBase.h" />
@@ -234,6 +238,8 @@
     <ClInclude Include="lexlib\WordList.h" />
     <ClInclude Include="src\AutoComplete.h" />
     <ClInclude Include="src\CallTip.h" />
+    <ClInclude Include="src\CaseConvert.h" />
+    <ClInclude Include="src\CaseFolder.h" />
     <ClInclude Include="src\Catalogue.h" />
     <ClInclude Include="src\CellBuffer.h" />
     <ClInclude Include="src\CharClassify.h" />
diff --git a/scintilla/Scintilla_icl13.vcxproj.filters b/scintilla/Scintilla_icl13.vcxproj.filters
index 8b57396..a22b24b 100644
--- a/scintilla/Scintilla_icl13.vcxproj.filters
+++ b/scintilla/Scintilla_icl13.vcxproj.filters
@@ -96,6 +96,9 @@
     <ClCompile Include="lexlib\Accessor.cxx">
       <Filter>lexlib</Filter>
     </ClCompile>
+    <ClCompile Include="lexlib\CharacterCategory.cxx">
+      <Filter>lexlib</Filter>
+    </ClCompile>
     <ClCompile Include="lexlib\CharacterSet.cxx">
       <Filter>lexlib</Filter>
     </ClCompile>
@@ -126,6 +129,12 @@
     <ClCompile Include="src\CallTip.cxx">
       <Filter>src</Filter>
     </ClCompile>
+    <ClCompile Include="src\CaseConvert.cxx">
+      <Filter>src</Filter>
+    </ClCompile>
+    <ClCompile Include="src\CaseFolder.cxx">
+      <Filter>src</Filter>
+    </ClCompile>
     <ClCompile Include="src\Catalogue.cxx">
       <Filter>src</Filter>
     </ClCompile>
@@ -212,6 +221,9 @@
     <ClInclude Include="lexlib\Accessor.h">
       <Filter>lexlib</Filter>
     </ClInclude>
+    <ClInclude Include="lexlib\CharacterCategory.h">
+      <Filter>lexlib</Filter>
+    </ClInclude>
     <ClInclude Include="lexlib\CharacterSet.h">
       <Filter>lexlib</Filter>
     </ClInclude>
@@ -254,6 +266,12 @@
     <ClInclude Include="src\CallTip.h">
       <Filter>src</Filter>
     </ClInclude>
+    <ClInclude Include="src\CaseConvert.h">
+      <Filter>src</Filter>
+    </ClInclude>
+    <ClInclude Include="src\CaseFolder.h">
+      <Filter>src</Filter>
+    </ClInclude>
     <ClInclude Include="src\Catalogue.h">
       <Filter>src</Filter>
     </ClInclude>
diff --git a/scintilla/cppcheck.suppress b/scintilla/cppcheck.suppress
index de777f8..b45634e 100644
--- a/scintilla/cppcheck.suppress
+++ b/scintilla/cppcheck.suppress
@@ -7,7 +7,6 @@
 useInitializationList
 
 // Suppress most lexer warnings since the lexers are maintained by others
-variableScope:scintilla/lexers/LexA68k.cxx
 useInitializationList:scintilla/lexers/LexAsm.cxx
 useInitializationList:scintilla/lexers/LexBasic.cxx
 noCopyConstructor:scintilla/lexers/LexBash.cxx
@@ -16,7 +15,6 @@ variableScope:scintilla/lexers/LexCmake.cxx
 variableScope:scintilla/lexers/LexCoffeeScript.cxx
 variableScope:scintilla/lexers/LexCSS.cxx
 useInitializationList:scintilla/lexers/LexD.cxx
-redundantCondition:scintilla/lexers/LexECL.cxx
 variableScope:scintilla/lexers/LexErlang.cxx
 variableScope:scintilla/lexers/LexFortran.cxx
 variableScope:scintilla/lexers/LexGui4Cli.cxx
@@ -31,7 +29,6 @@ variableScope:scintilla/lexers/LexOpal.cxx
 variableScope:scintilla/lexers/LexOthers.cxx
 variableScope:scintilla/lexers/LexPB.cxx
 variableScope:scintilla/lexers/LexPS.cxx
-uninitMemberVar:scintilla/lexers/LexPerl.cxx
 variableScope:scintilla/lexers/LexRuby.cxx
 uninitMemberVar:scintilla/lexers/LexRuby.cxx
 variableScope:scintilla/lexers/LexSpecman.cxx
diff --git a/scintilla/doc/ScintillaDoc.html b/scintilla/doc/ScintillaDoc.html
index 1c95c86..8c111b1 100644
--- a/scintilla/doc/ScintillaDoc.html
+++ b/scintilla/doc/ScintillaDoc.html
@@ -82,7 +82,7 @@
 

     <h1>Scintilla Documentation</h1>

 

-    <p>Last edited 5/May/2013 NH</p>

+    <p>Last edited 29/June/2013 NH</p>

 

     <p>There is <a class="jump" href="Design.html">an overview of the internal design of

     Scintilla</a>.<br />

@@ -115,6 +115,9 @@
     <p>The GTK+ version also uses messages in a similar way to the Windows version. This is

     different to normal GTK+ practice but made it easier to implement rapidly.</p>

 

+    <p>Scintilla also builds with Cocoa on OS X and with Qt, and follows the conventions of 

+    those platforms.</p>

+

     <p>Scintilla does not properly support right-to-left languages like Arabic and Hebrew.

     While text in these languages may appear correct, it is not possible to interact with this text

     as is normal with other editing components.</p>

@@ -1344,7 +1347,7 @@ struct Sci_TextToFind {
     <p><b id="SCI_GETLINESELSTARTPOSITION">SCI_GETLINESELSTARTPOSITION(int line)</b><br />

     <b id="SCI_GETLINESELENDPOSITION">SCI_GETLINESELENDPOSITION(int line)</b><br />

     Retrieve the position of the start and end of the selection at the given line with

-    INVALID_POSITION returned if no selection on this line.</p>

+    <code>INVALID_POSITION</code> returned if no selection on this line.</p>

 

     <p><b id="SCI_MOVECARETINSIDEVIEW">SCI_MOVECARETINSIDEVIEW</b><br />

      If the caret is off the top or bottom of the view, it is moved to the nearest line that is

@@ -6321,13 +6324,23 @@ exception options.</p>
 

 <p>

 To allow lexers to determine the end position of a line and thus more easily support Unicode line ends

-<code>IDocument</code> is extended to <code>IDocumentWithLineEnd</code>.

+<code>IDocument</code> is extended to <code>IDocumentWithLineEnd</code>.</p>

+<p><code>GetRelativePosition</code> navigates the document by whole characters,

+returning <code>INVALID_POSITION</code> for movement beyond the start and end of the document.</p>

+<p><code>GetCharacterAndWidth</code> provides a standard

+conversion from UTF-8 bytes to a UTF-32 character or from DBCS to a 16 bit value.

+Bytes in invalid UTF-8 are reported individually with values 0xDC80+byteValue, which are

+not valid Unicode code points.

+The <code>pWidth</code> argument can be NULL if the caller does not need to know the number of

+bytes in the character.

 </p>

 

 <div class="highlighted">

 <span class="S5">class</span><span class="S0"> </span>IDocumentWithLineEnd<span class="S0"> </span><span class="S10">:</span><span class="S0"> </span><span class="S5">public</span><span class="S0"> </span>IDocument<span class="S0"> </span><span class="S10">{</span><br />

 <span class="S5">public</span><span class="S10">:</span><br />

 <span class="S0">&nbsp; &nbsp; &nbsp; &nbsp; </span><span class="S5">virtual</span><span class="S0"> </span><span class="S5">int</span><span class="S0"> </span>SCI_METHOD<span class="S0"> </span>LineEnd<span class="S10">(</span><span class="S5">int</span><span class="S0"> </span>line<span class="S10">)</span><span class="S0"> </span><span class="S5">const</span><span class="S0"> </span><span class="S10">=</span><span class="S0"> </span><span class="S4">0</span><span class="S10">;</span><br />

+<span class="S0">&nbsp; &nbsp; &nbsp; &nbsp; </span><span class="S5">virtual</span><span class="S0"> </span><span class="S5">int</span><span class="S0"> </span>SCI_METHOD<span class="S0"> </span>GetRelativePosition<span class="S10">(</span><span class="S5">int</span><span class="S0"> </span>positionStart<span class="S10">,</span><span class="S0"> </span><span class="S5">int</span><span class="S0"> </span>characterOffset<span class="S10">)</span><span class="S0"> </span><span class="S5">const</span><span class="S0"> </span><span class="S10">=</span><span class="S0"> </span><span class="S4">0</span><span class="S10">;</span><br />

+<span class="S0">&nbsp; &nbsp; &nbsp; &nbsp; </span><span class="S5">virtual</span><span class="S0"> </span><span class="S5">int</span><span class="S0"> </span>SCI_METHOD<span class="S0"> </span>GetCharacterAndWidth<span class="S10">(</span><span class="S5">int</span><span class="S0"> </span>position<span class="S10">,</span><span class="S0"> </span><span class="S5">int</span><span class="S0"> </span><span class="S10">*</span>pWidth<span class="S10">)</span><span class="S0"> </span><span class="S5">const</span><span class="S0"> </span><span class="S10">=</span><span class="S0"> </span><span class="S4">0</span><span class="S10">;</span><br />

 <span class="S10">};</span><br />

 </div>

 

@@ -6602,9 +6615,7 @@ href="#SCI_POSITIONFROMLINE">SCI_POSITIONFROMLINE</a>(lineNumber);
 

           <td align="left">Valid for text changes, not for style changes. If we are collecting undo

           information this holds a pointer to the text that is handed to the Undo system, otherwise

-          it is zero. For user performed SC_MOD_BEFOREDELETE the text field is 0 and

-                  for user performed SC_MOD_BEFOREINSERT the text field points to an array of cells,

-                   not bytes and the length is the number of cells.</td>

+          it is zero. For user performed SC_MOD_BEFOREDELETE the text field is 0.</td>

         </tr>

 

         <tr>

diff --git a/scintilla/doc/ScintillaDownload.html b/scintilla/doc/ScintillaDownload.html
index 1e9b1f5..17e30fb 100644
--- a/scintilla/doc/ScintillaDownload.html
+++ b/scintilla/doc/ScintillaDownload.html
@@ -25,9 +25,9 @@
     <table bgcolor="#CCCCCC" width="100%" cellspacing="0" cellpadding="8" border="0">

       <tr>

         <td>

-          <font size="4"> <a href="http://prdownloads.sourceforge.net/scintilla/scintilla333.zip?download">

+          <font size="4"> <a href="http://prdownloads.sourceforge.net/scintilla/scintilla334.zip?download">

 	Windows</a>&nbsp;&nbsp;

-	<a href="http://prdownloads.sourceforge.net/scintilla/scintilla333.tgz?download">

+	<a href="http://prdownloads.sourceforge.net/scintilla/scintilla334.tgz?download">

           GTK+/Linux</a>&nbsp;&nbsp;

 	</font>

         </td>

@@ -41,7 +41,7 @@
       containing very few restrictions.

     </p>

     <h3>

-       Release 3.3.3

+       Release 3.3.4

     </h3>

     <h4>

        Source Code

@@ -49,8 +49,8 @@
        The source code package contains all of the source code for Scintilla but no binary

 	executable code and is available in

        <ul>

-       <li><a href="http://prdownloads.sourceforge.net/scintilla/scintilla333.zip?download">zip format</a> (1250K) commonly used on Windows</li>

-       <li><a href="http://prdownloads.sourceforge.net/scintilla/scintilla333.tgz?download">tgz format</a> (1100K) commonly used on Linux and compatible operating systems</li>

+       <li><a href="http://prdownloads.sourceforge.net/scintilla/scintilla334.zip?download">zip format</a> (1250K) commonly used on Windows</li>

+       <li><a href="http://prdownloads.sourceforge.net/scintilla/scintilla334.tgz?download">tgz format</a> (1100K) commonly used on Linux and compatible operating systems</li>

        </ul>

        Instructions for building on both Windows and Linux are included in the readme file.

     <h4>

diff --git a/scintilla/doc/ScintillaHistory.html b/scintilla/doc/ScintillaHistory.html
index b7179e6..c7911bf 100644
--- a/scintilla/doc/ScintillaHistory.html
+++ b/scintilla/doc/ScintillaHistory.html
@@ -425,6 +425,8 @@
 	<td>Igor Shaula</td>

 	<td>Pavel Bulochkin</td>

 	<td>Yosef Or Boczko</td>

+      </tr><tr>

+	<td>Brian Griffin</td>

     </tr>

     </table>

     <p>

@@ -437,6 +439,131 @@
       </li>

     </ul>

     <h3>

+       <a href="http://prdownloads.sourceforge.net/scintilla/scite334.zip?download">Release 3.3.4</a>

+    </h3>

+    <ul>

+	<li>

+	Released 19 July 2013.

+	</li>

+	<li>

+	Handling of UTF-8 and DBCS text in lexers improved with methods ForwardBytes and

+	GetRelativeCharacter added to StyleContext.

+	<a href="http://sourceforge.net/p/scintilla/bugs/1483/">Bug #1483</a>.

+	</li>

+	<li>

+	For Unicode text, case-insensitive searching and making text upper or lower case is now

+	compliant with Unicode standards on all platforms and is much faster for non-ASCII characters.

+	</li>

+	<li>

+	A CategoriseCharacter function was added to return the Unicode general category of a character

+	which can be useful in lexers.

+	</li>

+	<li>

+	On Cocoa, the LCD Optimized font quality level turns font smoothing on.

+	</li>

+	<li>

+	SciTE 'immediate' subsystem added to allow scripts that work while tools are executed.

+	</li>

+	<li>

+	Font quality exposed in SciTE as font.quality setting.

+	</li>

+	<li>

+	On Cocoa, message:... methods simplify direct access to Scintilla and avoid call layers..

+	</li>

+	<li>

+	A68K lexer updated.

+	</li>

+	<li>

+	CoffeeScript lexer fixes a bug with comment blocks.

+	<a href="http://sourceforge.net/p/scintilla/feature-requests/1495/">Feature #1495.</a>

+	</li>

+	<li>

+	ECL lexer regular expression code fixed.

+	<a href="http://sourceforge.net/p/scintilla/bugs/1491/">Bug #1491</a>.

+	</li>

+	<li>

+	errorlist lexer only recognises Perl diagnostics when there is a filename between

+	"at" and "line". Had been triggering for MSVC errors containing "at line".

+	</li>

+	<li>

+	Haskell lexer fixed to avoid unnecessary full redraws.

+	Don't highlight CPP inside comments when styling.within.preprocessor is on.

+	<a href="http://sourceforge.net/p/scintilla/bugs/1459/">Bug #1459</a>.

+	</li>

+	<li>

+	Lua lexer fixes bug in labels with UTF-8 text.

+	<a href="http://sourceforge.net/p/scintilla/bugs/1483/">Bug #1483</a>.

+	</li>

+	<li>

+	Perl lexer fixes bug in string interpolation with UTF-8 text.

+	<a href="http://sourceforge.net/p/scintilla/bugs/1483/">Bug #1483</a>.

+	</li>

+	<li>

+	Fixed bugs with case conversion when the result was longer or shorter than the original text.

+	Could access past end of string potentially crashing.

+	Selection now updated to result length.

+	</li>

+	<li>

+	Fixed bug where data being inserted and removed was not being reported in

+	notification messages. Bug was introduced in 3.3.2.

+	</li>

+	<li>

+	Word wrap bug fixed where the last line could be shown twice.

+	</li>

+	<li>

+	Word wrap bug fixed for lines wrapping too short on Windows and GTK+.

+	</li>

+	<li>

+	Word wrap performance improved.

+	</li>

+	<li>

+	Minor memory leak fixed.

+	<a href="http://sourceforge.net/p/scintilla/bugs/1487/">Bug #1487</a>.

+	</li>

+	<li>

+	On Cocoa, fixed insertText: method which was broken when implementing a newer protocol.

+	</li>

+	<li>

+	On Cocoa, fixed a crash when performing string folding for bytes that do not represent a character

+	in the current encoding.

+	</li>

+	<li>

+	On Qt, fixed layout problem when QApplication construction delayed.

+	</li>

+	<li>

+	On Qt, find_text reports failure with -1 as first element of return value.

+	</li>

+	<li>

+	Fixed SciTE on GTK+ bug where a tool command could be performed using the keyboard while one was

+	already running leading to confusion and crashes.

+	<a href="http://sourceforge.net/p/scintilla/bugs/1486/">Bug #1486</a>.

+	</li>

+	<li>

+	Fixed SciTE bug in Copy as RTF which was limited to first 32 styles.

+	<a href="http://sourceforge.net/p/scintilla/bugs/1011/">Bug #1011</a>.

+	</li>

+	<li>

+	Fixed SciTE on Windows user strip height when the system text scaling factor is 125% or 150%.

+	</li>

+	<li>

+	Compile time checks for Digital Mars C++ removed.

+	</li>

+	<li>

+	Visual C++ 2013 supported.

+	<a href="http://sourceforge.net/p/scintilla/bugs/1492/">Bug #1492</a>.

+	</li>

+	<li>

+	Python scripts used for building and maintenance improved and moved into scripts directory.

+	</li>

+	<li>

+	Testing scripts now work on Linux using Qt and PySide.

+	</li>

+	<li>

+	Tk platform defined.

+	Implementation for Tk will be available separately from main Scintilla distribution.

+	</li>

+    </ul>

+    <h3>

        <a href="http://prdownloads.sourceforge.net/scintilla/scite333.zip?download">Release 3.3.3</a>

     </h3>

     <ul>

diff --git a/scintilla/doc/index.html b/scintilla/doc/index.html
index d916e18..357fc48 100644
--- a/scintilla/doc/index.html
+++ b/scintilla/doc/index.html
@@ -9,7 +9,7 @@
     <meta name="keywords" content="Scintilla, SciTE, Editing Component, Text Editor" />

     <meta name="Description"

     content="www.scintilla.org is the home of the Scintilla editing component and SciTE text editor application." />

-    <meta name="Date.Modified" content="20130602" />

+    <meta name="Date.Modified" content="20130719" />

     <style type="text/css">

         #versionlist {

             margin: 0;

@@ -51,12 +51,12 @@
           <img src="SciWord.jpg" height="78" width="256" alt="Scintilla" />

         </td>

         <td width="40%" align="left">

-          <font color="#FFCC99" size="4"> A free source code editing component for Win32 and

-          GTK+</font>

+          <font color="#FFCC99" size="4"> A free source code editing component for Win32,

+          GTK+, and OS X</font>

         </td>

         <td width="40%" align="right">

-          <font color="#FFCC99" size="3"> Release version 3.3.3<br />

-           Site last modified June 2 2013</font>

+          <font color="#FFCC99" size="3"> Release version 3.3.4<br />

+           Site last modified July 19 2013</font>

         </td>

         <td width="20%">

           &nbsp;

@@ -71,6 +71,7 @@
       </tr>

     </table>

     <ul id="versionlist">

+      <li>Version 3.3.4 better supports Unicode use in lexers.</li>

       <li>Version 3.3.3 fixes bugs on GTK+.</li>

       <li>Version 3.3.2 simplifies implementing folding.</li>

       <li>Version 3.3.1 fixes bugs on Cocoa.</li>

@@ -124,8 +125,8 @@ if (!IsRemote()) { //if NOT remote...
       code, styling should not be persisted as it can be mechanically recreated.

     </p>

     <p>

-       Scintilla and SciTE are currently available for Intel Win32 and Linux compatible operating

-      systems with GTK+. They have been run on Windows XP, Windows 7, and on Ubuntu 10.10

+       Scintilla and SciTE are currently available for Intel Win32, OS X, and Linux compatible operating

+      systems with GTK+. They have been run on Windows XP, Windows 7, OS X 10.6+, and on Ubuntu 10.10

       with GTK+ 2.20. <a href="http://www.scintilla.org/SciTEImage.html">Here is a screenshot of

       SciTE.</a><br />

     </p>

diff --git a/scintilla/include/Face.py b/scintilla/include/Face.py
deleted file mode 100644
index 2cf4b89..0000000
--- a/scintilla/include/Face.py
+++ /dev/null
@@ -1,114 +0,0 @@
-# Module for reading and parsing Scintilla.iface file

-

-def sanitiseLine(line):

-	if line[-1:] == '\n': line = line[:-1]

-	if line.find("##") != -1:

-		line = line[:line.find("##")]

-	line = line.strip()

-	return line

-	

-def decodeFunction(featureVal):

-	retType, rest = featureVal.split(" ", 1)

-	nameIdent, params = rest.split("(")

-	name, value = nameIdent.split("=")

-	params, rest = params.split(")")

-	param1, param2 = params.split(",")

-	return retType, name, value, param1, param2

-	

-def decodeEvent(featureVal):

-	retType, rest = featureVal.split(" ", 1)

-	nameIdent, params = rest.split("(")

-	name, value = nameIdent.split("=")

-	return retType, name, value

-	

-def decodeParam(p):

-	param = p.strip()

-	type = ""

-	name = ""

-	value = ""

-	if " " in param:

-		type, nv = param.split(" ")

-		if "=" in nv:

-			name, value = nv.split("=")

-		else:

-			name = nv

-	return type, name, value

-

-class Face:

-

-	def __init__(self):

-		self.order = []

-		self.features = {}

-		self.values = {}

-		self.events = {}

-		

-	def ReadFromFile(self, name):

-		currentCategory = ""

-		currentComment = []

-		currentCommentFinished = 0

-		file = open(name)

-		for line in file.readlines():

-			line = sanitiseLine(line)

-			if line:

-				if line[0] == "#":

-					if line[1] == " ":

-						if currentCommentFinished:

-							currentComment = []

-							currentCommentFinished = 0

-						currentComment.append(line[2:])

-				else:

-					currentCommentFinished = 1

-					featureType, featureVal = line.split(" ", 1)

-					if featureType in ["fun", "get", "set"]:

-						try:

-							retType, name, value, param1, param2 = decodeFunction(featureVal)

-						except ValueError:

-							print("Failed to decode %s" % line)

-							raise

-						p1 = decodeParam(param1)

-						p2 = decodeParam(param2)

-						self.features[name] = { 

-							"FeatureType": featureType, 

-							"ReturnType": retType,

-							"Value": value, 

-							"Param1Type": p1[0], "Param1Name": p1[1], "Param1Value": p1[2], 

-							"Param2Type": p2[0],	"Param2Name": p2[1], "Param2Value": p2[2],

-							"Category": currentCategory, "Comment": currentComment

-						}

-						if value in self.values:

-							raise Exception("Duplicate value " + value + " " + name)

-						self.values[value] = 1

-						self.order.append(name)

-					elif featureType == "evt":

-						retType, name, value = decodeEvent(featureVal)

-						self.features[name] = { 

-							"FeatureType": featureType, 

-							"ReturnType": retType,

-							"Value": value, 

-							"Category": currentCategory, "Comment": currentComment

-						}

-						if value in self.events:

-							raise Exception("Duplicate event " + value + " " + name)

-						self.events[value] = 1

-						self.order.append(name)

-					elif featureType == "cat":

-						currentCategory = featureVal

-					elif featureType == "val":

-						try:

-							name, value = featureVal.split("=", 1)

-						except ValueError:

-							print("Failure %s" % featureVal)

-							raise Exception()

-						self.features[name] = { 

-							"FeatureType": featureType, 

-							"Category": currentCategory, 

-							"Value": value }

-						self.order.append(name)

-					elif featureType == "enu" or featureType == "lex":

-						name, value = featureVal.split("=", 1)

-						self.features[name] = { 

-							"FeatureType": featureType, 

-							"Category": currentCategory, 

-							"Value": value }

-						self.order.append(name)

-

diff --git a/scintilla/include/HFacer.py b/scintilla/include/HFacer.py
deleted file mode 100644
index 911b703..0000000
--- a/scintilla/include/HFacer.py
+++ /dev/null
@@ -1,81 +0,0 @@
-#!/usr/bin/env python

-# HFacer.py - regenerate the Scintilla.h and SciLexer.h files from the Scintilla.iface interface

-# definition file.

-# The header files are copied to a temporary file apart from the section between a /* ++Autogenerated*/

-# comment and a /* --Autogenerated*/ comment which is generated by the printHFile and printLexHFile

-# functions. After the temporary file is created, it is copied back to the original file name.

-

-import sys

-import os

-import Face

-

-def Contains(s,sub):

-	return s.find(sub) != -1

-

-def printLexHFile(f,out):

-	for name in f.order:

-		v = f.features[name]

-		if v["FeatureType"] in ["val"]:

-			if Contains(name, "SCE_") or Contains(name, "SCLEX_"):

-				out.write("#define " + name + " " + v["Value"] + "\n")

-

-def printHFile(f,out):

-	previousCategory = ""

-	for name in f.order:

-		v = f.features[name]

-		if v["Category"] != "Deprecated":

-			if v["Category"] == "Provisional" and previousCategory != "Provisional":

-				out.write("#ifndef SCI_DISABLE_PROVISIONAL\n")

-			previousCategory = v["Category"]

-			if v["FeatureType"] in ["fun", "get", "set"]:

-				featureDefineName = "SCI_" + name.upper()

-				out.write("#define " + featureDefineName + " " + v["Value"] + "\n")

-			elif v["FeatureType"] in ["evt"]:

-				featureDefineName = "SCN_" + name.upper()

-				out.write("#define " + featureDefineName + " " + v["Value"] + "\n")

-			elif v["FeatureType"] in ["val"]:

-				if not (Contains(name, "SCE_") or Contains(name, "SCLEX_")):

-					out.write("#define " + name + " " + v["Value"] + "\n")

-	out.write("#endif\n")

-

-def CopyWithInsertion(input, output, genfn, definition):

-	copying = 1

-	for line in input.readlines():

-		if copying:

-			output.write(line)

-		if Contains(line, "/* ++Autogenerated"):

-			copying = 0

-			genfn(definition, output)

-		if Contains(line, "/* --Autogenerated"):

-			copying = 1

-			output.write(line)

-

-def contents(filename):

-	f = open(filename)

-	t = f.read()

-	f.close()

-	return t

-

-def Regenerate(filename, genfn, definition):

-	inText = contents(filename)

-	tempname = "HFacer.tmp"

-	out = open(tempname,"w")

-	hfile = open(filename)

-	CopyWithInsertion(hfile, out, genfn, definition)

-	out.close()

-	hfile.close()

-	outText = contents(tempname)

-	if inText == outText:

-		os.unlink(tempname)

-	else:

-		os.unlink(filename)

-		os.rename(tempname, filename)

-

-f = Face.Face()

-try:

-	f.ReadFromFile("Scintilla.iface")

-	Regenerate("Scintilla.h", printHFile, f)

-	Regenerate("SciLexer.h", printLexHFile, f)

-	print("Maximum ID is %s" % max([x for x in f.values if int(x) < 3000]))

-except:

-	raise

diff --git a/scintilla/include/ILexer.h b/scintilla/include/ILexer.h
index 795a7d7..5b6ed6f 100644
--- a/scintilla/include/ILexer.h
+++ b/scintilla/include/ILexer.h
@@ -48,6 +48,8 @@ public:
 class IDocumentWithLineEnd : public IDocument {

 public:

 	virtual int SCI_METHOD LineEnd(int line) const = 0;

+	virtual int SCI_METHOD GetRelativePosition(int positionStart, int characterOffset) const = 0;

+	virtual int SCI_METHOD GetCharacterAndWidth(int position, int *pWidth) const = 0;

 };

 

 enum { lvOriginal=0, lvSubStyles=1 };

diff --git a/scintilla/include/Platform.h b/scintilla/include/Platform.h
index 2769a9f..6103301 100644
--- a/scintilla/include/Platform.h
+++ b/scintilla/include/Platform.h
@@ -13,6 +13,7 @@
 // PLAT_GTK_WIN32 is defined additionally when running PLAT_GTK under Win32

 // PLAT_WIN = Win32 API on Win32 OS

 // PLAT_WX is wxWindows on any supported platform

+// PLAT_TK = Tcl/TK on Linux or Win32

 

 #define PLAT_GTK 0

 #define PLAT_GTK_WIN32 0

@@ -23,6 +24,7 @@
 #define PLAT_QT 0

 #define PLAT_FOX 0

 #define PLAT_CURSES 0

+#define PLAT_TK 0

 

 #if defined(FOX)

 #undef PLAT_FOX

@@ -40,6 +42,10 @@
 #undef PLAT_QT

 #define PLAT_QT 1

 

+#elif defined(TK)

+#undef PLAT_TK

+#define PLAT_TK 1

+

 #elif defined(GTK)

 #undef PLAT_GTK

 #define PLAT_GTK 1

diff --git a/scintilla/lexers/LexA68k.cxx b/scintilla/lexers/LexA68k.cxx
index cbf2681..81f26ce 100644
--- a/scintilla/lexers/LexA68k.cxx
+++ b/scintilla/lexers/LexA68k.cxx
@@ -117,13 +117,20 @@ static inline bool IsDoxygenChar (const int ch)
 

 static void ColouriseA68kDoc (unsigned int startPos, int length, int initStyle, WordList *keywordlists[], Accessor &styler)

 {

+    // Used to buffer a string, to be able to compare it using built-in functions 

+    char Buffer[100]; 

+ 

+ 

+    // Used to know the length of an operator 

+    int OpType; 

+ 

 

     // Get references to keywords lists

     WordList &cpuInstruction = *keywordlists[0];

     WordList &registers = *keywordlists[1];

     WordList &directive = *keywordlists[2];

     WordList &extInstruction = *keywordlists[3];

-    WordList &commentSpecial = *keywordlists[4];

+    WordList &alert          = *keywordlists[4]; 

     WordList &doxygenKeyword = *keywordlists[5];

 

 

@@ -133,103 +140,109 @@ static void ColouriseA68kDoc (unsigned int startPos, int length, int initStyle,
 

     /************************************************************

     *

-    *   Parse the text

+    *   Parse the source 

     *

     ************************************************************/

 

     for ( ; sc.More(); sc.Forward())

     {

-        char Buffer[100];

-        int OpType;

-

-        // Reset style at beginning of line

-        if (sc.atLineStart)

+        /************************************************************ 

+        * 

+        *   A style always terminates at the end of a line, even for 

+        *   comments (no multi-lines comments) 

+        * 

+        ************************************************************/ 

+        if (sc.atLineStart) { 

             sc.SetState(SCE_A68K_DEFAULT);

+        } 

 

 

         /************************************************************

         *

-        *   Handle current state if we are not in the "default style"

+        *   If we are not in "default style", check if the style continues 

+        *   In this case, we just have to loop 

         *

         ************************************************************/

 

         if (sc.state != SCE_A68K_DEFAULT)

         {

-            // Check if current style continue.

-            // If this case, we loop because there is nothing else to do

-            if (((sc.state == SCE_A68K_NUMBER_DEC) && isdigit(sc.ch))                                       // Decimal number

+            if (   ((sc.state == SCE_A68K_NUMBER_DEC)        && isdigit(sc.ch))                      // Decimal number 

                 || ((sc.state == SCE_A68K_NUMBER_BIN) && IsBin(sc.ch))                                      // Binary number

                 || ((sc.state == SCE_A68K_NUMBER_HEX) && isxdigit(sc.ch))                                   // Hexa number

-                || ((sc.state == SCE_A68K_MACRO_ARG)  && isdigit(sc.ch))                                    // Arg of macro

+                || ((sc.state == SCE_A68K_MACRO_ARG)         && isdigit(sc.ch))                      // Macro argument 

                 || ((sc.state == SCE_A68K_STRING1)    && (sc.ch != '\''))                                   // String single-quoted

                 || ((sc.state == SCE_A68K_STRING2)    && (sc.ch != '\"'))                                   // String double-quoted

-                || ((sc.state == SCE_A68K_MACRO_ARG)  && isdigit(sc.ch))                                    // Macro argument

-                // Label. ' ' and '\t' are needed to handle macro declarations

-                || ((sc.state == SCE_A68K_LABEL)      && (sc.ch != ':') && (sc.ch != ' ') && (sc.ch != '\t'))

-                || ((sc.state == SCE_A68K_IDENTIFIER) && (sc.ch < 0x80) && IsIdentifierChar(sc.ch))         // Identifier

-                || ((sc.state == SCE_A68K_COMMENT_DOXYGEN) && (sc.ch < 0x80) && IsDoxygenChar(sc.ch))       // Doxygen keyword

-                || ((sc.state == SCE_A68K_COMMENT_WORD) && (sc.ch < 0x80) && isalpha(sc.ch)))               // Comment current word

+                || ((sc.state == SCE_A68K_MACRO_DECLARATION) && IsIdentifierChar(sc.ch))             // Macro declaration (or global label, we don't know at this point) 

+                || ((sc.state == SCE_A68K_IDENTIFIER)        && IsIdentifierChar(sc.ch))             // Identifier 

+                || ((sc.state == SCE_A68K_LABEL)             && IsIdentifierChar(sc.ch))             // Label (local) 

+                || ((sc.state == SCE_A68K_COMMENT_DOXYGEN)   && IsDoxygenChar(sc.ch))                // Doxygen keyword 

+                || ((sc.state == SCE_A68K_COMMENT_SPECIAL)   && isalpha(sc.ch))                      // Alert 

+                || ((sc.state == SCE_A68K_COMMENT)           && !isalpha(sc.ch) && (sc.ch != '\\'))) // Normal comment 

             {

                 continue;

             }

 

-            // Check if some states terminate at the current char:

-            // we must include this char in the current style context

-            else if (((sc.state == SCE_A68K_STRING1)    && (sc.ch < 0x80) && (sc.ch == '\''))       // String single-quoted

-                     || ((sc.state == SCE_A68K_STRING2) && (sc.ch < 0x80) && (sc.ch == '\"'))       // String double-quoted

-                     || ((sc.state == SCE_A68K_LABEL)   && (sc.ch < 0x80) && (sc.ch == ':')))       // Label

-            {

-                sc.ForwardSetState(SCE_A68K_DEFAULT);

-            }

+        /************************************************************ 

+        * 

+        *   Check if current state terminates 

+        * 

+        ************************************************************/ 

 

-            // Check for special words or Doxygen keywords in comments

-            else if (sc.state == SCE_A68K_COMMENT)

-            {

-                if (sc.ch == '\\') {

-                    sc.SetState(SCE_A68K_COMMENT_DOXYGEN);

-                }

-                else if ((sc.ch < 0x80) && isalpha(sc.ch)) {

-                    sc.SetState(SCE_A68K_COMMENT_WORD);

+            // Strings: include terminal ' or " in the current string by skipping it 

+            if ((sc.state == SCE_A68K_STRING1) || (sc.state == SCE_A68K_STRING2)) { 

+                sc.Forward(); 

                 }

-                continue;

+ 

+ 

+            // If a macro declaration was terminated with ':', it was a label 

+            else if ((sc.state == SCE_A68K_MACRO_DECLARATION) && (sc.chPrev == ':')) { 

+                sc.ChangeState(SCE_A68K_LABEL); 

             }

 

-            // Check for special words in comment

-            else if ((sc.state == SCE_A68K_COMMENT_WORD) && (sc.ch < 0x80) && !isalpha(sc.ch))

-            {

+ 

+            // If it wasn't a Doxygen keyword, change it to normal comment 

+            else if (sc.state == SCE_A68K_COMMENT_DOXYGEN) { 

                 sc.GetCurrent(Buffer, sizeof(Buffer));

-                if (commentSpecial.InList(Buffer)) {

-                    sc.ChangeState(SCE_A68K_COMMENT_SPECIAL);

-                }

-                else {

+                if (!doxygenKeyword.InList(Buffer)) { 

                     sc.ChangeState(SCE_A68K_COMMENT);

                 }

                 sc.SetState(SCE_A68K_COMMENT);

                 continue;

             }

 

-            // Check for Doxygen keywords

-            else if ((sc.state == SCE_A68K_COMMENT_DOXYGEN) && (sc.ch < 0x80) && !IsDoxygenChar(sc.ch))

-            {

-                sc.GetCurrentLowered(Buffer, sizeof(Buffer));                           // Buffer the string of the current context

-                if (!doxygenKeyword.InList(Buffer)) {

+ 

+            // If it wasn't an Alert, change it to normal comment 

+            else if (sc.state == SCE_A68K_COMMENT_SPECIAL) { 

+                sc.GetCurrent(Buffer, sizeof(Buffer)); 

+                if (!alert.InList(Buffer)) { 

                     sc.ChangeState(SCE_A68K_COMMENT);

                 }

+                // Reset style to normal comment, or to Doxygen keyword if it begins with '\'  

+                if (sc.ch == '\\') { 

+                    sc.SetState(SCE_A68K_COMMENT_DOXYGEN); 

+                } 

+                else { 

                 sc.SetState(SCE_A68K_COMMENT);

+                } 

                 continue;

             }

 

-            // Check if we are in the case of a label which terminates without ':'

-            // It should be a macro declaration, not a label

-            else if ((sc.state == SCE_A68K_LABEL) && (sc.ch < 0x80) && ((sc.ch == ' ') || (sc.ch == '\t')))

-            {

-                sc.ChangeState(SCE_A68K_MACRO_DECLARATION);

+ 

+            // If we are in a comment, it's a Doxygen keyword or an Alert 

+            else if (sc.state == SCE_A68K_COMMENT) { 

+                if (sc.ch == '\\') { 

+                    sc.SetState(SCE_A68K_COMMENT_DOXYGEN); 

+                } 

+                else { 

+                    sc.SetState(SCE_A68K_COMMENT_SPECIAL); 

+                } 

+                continue; 

             }

 

+ 

             // Check if we are at the end of an identifier

             // In this case, colourise it if was a keyword.

-            else if ((sc.state == SCE_A68K_IDENTIFIER) && !IsIdentifierChar(sc.ch))

-            {

+            else if ((sc.state == SCE_A68K_IDENTIFIER) && !IsIdentifierChar(sc.ch)) { 

                 sc.GetCurrentLowered(Buffer, sizeof(Buffer));                           // Buffer the string of the current context

                 if (cpuInstruction.InList(Buffer)) {                                    // And check if it belongs to a keyword list

                     sc.ChangeState(SCE_A68K_CPUINSTRUCTION);

@@ -256,14 +269,30 @@ static void ColouriseA68kDoc (unsigned int startPos, int length, int initStyle,
         *

         ************************************************************/

 

+        // Something which begins at the beginning of a line, and with  

+        // - '\' + an identifier start char, or 

+        // - '\\@' + an identifier start char 

+        // is a local label (second case is used for macro local labels). We set it already as a label, it can't be a macro/equ declaration 

+        if (sc.atLineStart && (sc.ch < 0x80) && IsIdentifierStart(sc.chNext) && (sc.ch == '\\')) { 

+            sc.SetState(SCE_A68K_LABEL); 

+        } 

+ 

+        if (sc.atLineStart && (sc.ch < 0x80) && (sc.ch == '\\') && (sc.chNext == '\\')) { 

+            sc.Forward(2); 

+            if ((sc.ch == '@') && IsIdentifierStart(sc.chNext)) { 

+                sc.ChangeState(SCE_A68K_LABEL); 

+                sc.SetState(SCE_A68K_LABEL); 

+            } 

+        } 

+         

         // Label and macro identifiers start at the beginning of a line

-        // We set both as a label, but if it wasn't one (no ':' at the end),

-        // it will be changed as a macro identifier.

+        // We set both as a macro id, but if it wasn't one (':' at the end), 

+        // it will be changed as a label. 

         if (sc.atLineStart && (sc.ch < 0x80) && IsIdentifierStart(sc.ch)) {

-            sc.SetState(SCE_A68K_LABEL);

+            sc.SetState(SCE_A68K_MACRO_DECLARATION); 

         }

-        else if ((sc.ch < 0x80) && (sc.ch == ';')) {                            // Comment

-            sc.SetState(SCE_A68K_COMMENT);

+        else if ((sc.ch < 0x80) && (sc.ch == ';')) {                            // Default: alert in a comment. If it doesn't match 

+            sc.SetState(SCE_A68K_COMMENT);                                      // with an alert, it will be toggle to a normal comment 

         }

         else if ((sc.ch < 0x80) && isdigit(sc.ch)) {                            // Decimal numbers haven't prefix

             sc.SetState(SCE_A68K_NUMBER_DEC);

@@ -280,7 +309,7 @@ static void ColouriseA68kDoc (unsigned int startPos, int length, int initStyle,
         else if ((sc.ch < 0x80) && (sc.ch == '\"')) {                           // String (double-quoted)

             sc.SetState(SCE_A68K_STRING2);

         }

-        else if ((sc.ch < 0x80) && (sc.ch == '\\') && (isdigit(sc.chNext))) {   // Replacement symbols in macro

+        else if ((sc.ch < 0x80) && (sc.ch == '\\') && (isdigit(sc.chNext))) {   // Replacement symbols in macro are prefixed with '\' 

             sc.SetState(SCE_A68K_MACRO_ARG);

         }

         else if ((sc.ch < 0x80) && IsIdentifierStart(sc.ch)) {                  // An identifier: constant, label, etc...

diff --git a/scintilla/lexers/LexAda.cxx b/scintilla/lexers/LexAda.cxx
index 47a408b..67e89af 100644
--- a/scintilla/lexers/LexAda.cxx
+++ b/scintilla/lexers/LexAda.cxx
@@ -65,8 +65,6 @@ static void ColouriseWhiteSpace(StyleContext& sc, bool& apostropheStartsAttribut
 static void ColouriseWord(StyleContext& sc, WordList& keywords, bool& apostropheStartsAttribute);

 

 static inline bool IsDelimiterCharacter(int ch);

-static inline bool IsNumberStartCharacter(int ch);

-static inline bool IsNumberCharacter(int ch);

 static inline bool IsSeparatorOrDelimiterCharacter(int ch);

 static bool IsValidIdentifier(const std::string& identifier);

 static bool IsValidNumber(const std::string& number);

@@ -310,19 +308,6 @@ static inline bool IsDelimiterCharacter(int ch) {
 	}

 }

 

-static inline bool IsNumberCharacter(int ch) {

-	return IsNumberStartCharacter(ch) ||

-	       ch == '_' ||

-	       ch == '.' ||

-	       ch == '#' ||

-	       (ch >= 'a' && ch <= 'f') ||

-	       (ch >= 'A' && ch <= 'F');

-}

-

-static inline bool IsNumberStartCharacter(int ch) {

-	return IsADigit(ch);

-}

-

 static inline bool IsSeparatorOrDelimiterCharacter(int ch) {

 	return IsASpace(ch) || IsDelimiterCharacter(ch);

 }

diff --git a/scintilla/lexers/LexAsn1.cxx b/scintilla/lexers/LexAsn1.cxx
index dd168a7..90b8917 100644
--- a/scintilla/lexers/LexAsn1.cxx
+++ b/scintilla/lexers/LexAsn1.cxx
@@ -185,4 +185,4 @@ static const char * const asn1WordLists[] = {
 	0, };

 

 

-LexerModule lmAns1(SCLEX_ASN1, ColouriseAsn1Doc, "asn1", FoldAsn1Doc, asn1WordLists);

+LexerModule lmAsn1(SCLEX_ASN1, ColouriseAsn1Doc, "asn1", FoldAsn1Doc, asn1WordLists);

diff --git a/scintilla/lexers/LexCoffeeScript.cxx b/scintilla/lexers/LexCoffeeScript.cxx
index 3e51709..3b8d741 100644
--- a/scintilla/lexers/LexCoffeeScript.cxx
+++ b/scintilla/lexers/LexCoffeeScript.cxx
@@ -137,7 +137,7 @@ static void ColouriseCoffeeScriptDoc(unsigned int startPos, int length, int init
 

 	// look back to set chPrevNonWhite properly for better regex colouring

 	int endPos = startPos + length;

-	if (startPos > 0) {

+        if (startPos > 0 && IsSpaceEquiv(initStyle)) {

 		unsigned int back = startPos;

 		styler.Flush();

 		while (back > 0 && IsSpaceEquiv(styler.StyleAt(--back)))

@@ -147,6 +147,9 @@ static void ColouriseCoffeeScriptDoc(unsigned int startPos, int length, int init
 		}

 		if (startPos != back) {

 			initStyle = styler.StyleAt(back);

+			if (IsSpaceEquiv(initStyle)) {

+				initStyle = SCE_C_DEFAULT;

+			}

 		}

 		startPos = back;

 	}

@@ -321,7 +324,6 @@ static void ColouriseCoffeeScriptDoc(unsigned int startPos, int length, int init
 				break;

 			case SCE_COFFEESCRIPT_COMMENTBLOCK:

 				if (sc.Match("###")) {

-					sc.ChangeState(SCE_C_COMMENT);

 					sc.Forward();

 					sc.Forward();

 					sc.ForwardSetState(SCE_C_DEFAULT);

@@ -333,10 +335,8 @@ static void ColouriseCoffeeScriptDoc(unsigned int startPos, int length, int init
 				if (sc.Match("///")) {

 					sc.Forward();

 					sc.Forward();

-					sc.ChangeState(SCE_C_REGEX);

 					sc.ForwardSetState(SCE_C_DEFAULT);

 				} else if (sc.Match('#')) {

-					sc.ChangeState(SCE_C_REGEX);

 					sc.SetState(SCE_COFFEESCRIPT_VERBOSE_REGEX_COMMENT);

 				} else if (sc.ch == '\\') {

 					sc.Forward();

@@ -344,7 +344,6 @@ static void ColouriseCoffeeScriptDoc(unsigned int startPos, int length, int init
 				break;

 			case SCE_COFFEESCRIPT_VERBOSE_REGEX_COMMENT:

 				if (sc.atLineStart) {

-					sc.ChangeState(SCE_C_COMMENT);

 					sc.SetState(SCE_COFFEESCRIPT_VERBOSE_REGEX);

 				}

 				break;

@@ -378,6 +377,8 @@ static void ColouriseCoffeeScriptDoc(unsigned int startPos, int length, int init
 				sc.Forward();	// Eat the * so it isn't used for the end of the comment

 			} else if (sc.Match("///")) {

 				sc.SetState(SCE_COFFEESCRIPT_VERBOSE_REGEX);

+				sc.Forward();

+				sc.Forward();

 			} else if (sc.ch == '/'

 				   && (setOKBeforeRE.Contains(chPrevNonWhite)

 				       || followsReturnKeyword(sc, styler))

@@ -392,11 +393,14 @@ static void ColouriseCoffeeScriptDoc(unsigned int startPos, int length, int init
 			} else if (sc.ch == '\'') {

 				sc.SetState(SCE_C_CHARACTER);

 			} else if (sc.ch == '#') {

-                if (sc.Match("###")) {

-                    sc.SetState(SCE_COFFEESCRIPT_COMMENTBLOCK);

-                } else {

-                    sc.SetState(SCE_C_COMMENTLINE);

-                }

+				if (sc.Match("###")) {

+					sc.SetState(SCE_COFFEESCRIPT_COMMENTBLOCK);

+					sc.Forward();

+					sc.Forward();

+					

+				} else {

+					sc.SetState(SCE_C_COMMENTLINE);

+				}

 			} else if (isoperator(static_cast<char>(sc.ch))) {

 				sc.SetState(SCE_C_OPERATOR);

 			}

@@ -408,18 +412,6 @@ static void ColouriseCoffeeScriptDoc(unsigned int startPos, int length, int init
 		}

 		continuationLine = false;

 	}

-    // Change temporary coffeescript states into standard C ones.

-    switch (sc.state) {

-        case SCE_COFFEESCRIPT_COMMENTBLOCK:

-            sc.ChangeState(SCE_C_COMMENT);

-            break;

-        case SCE_COFFEESCRIPT_VERBOSE_REGEX:

-            sc.ChangeState(SCE_C_REGEX);

-            break;

-        case SCE_COFFEESCRIPT_VERBOSE_REGEX_COMMENT:

-            sc.ChangeState(SCE_C_COMMENTLINE);

-            break;

-    }

 	sc.Complete();

 }

 

diff --git a/scintilla/lexers/LexECL.cxx b/scintilla/lexers/LexECL.cxx
index 2db55a3..c55ef83 100644
--- a/scintilla/lexers/LexECL.cxx
+++ b/scintilla/lexers/LexECL.cxx
@@ -47,10 +47,19 @@ using namespace Scintilla;
 #endif

 

 static bool IsSpaceEquiv(int state) {

-	return (state <= SCE_ECL_COMMENTDOC) ||

-		// including SCE_ECL_DEFAULT, SCE_ECL_COMMENT, SCE_ECL_COMMENTLINE

-		(state == SCE_ECL_COMMENTLINEDOC) || (state == SCE_ECL_COMMENTDOCKEYWORD) ||

-		(state == SCE_ECL_COMMENTDOCKEYWORDERROR);

+	switch (state) {

+	case SCE_ECL_DEFAULT:

+	case SCE_ECL_COMMENT:

+	case SCE_ECL_COMMENTLINE:

+	case SCE_ECL_COMMENTLINEDOC:

+	case SCE_ECL_COMMENTDOCKEYWORD:

+	case SCE_ECL_COMMENTDOCKEYWORDERROR:

+	case SCE_ECL_COMMENTDOC:

+		return true;

+

+	default:

+		return false;

+	}

 }

 

 static void ColouriseEclDoc(unsigned int startPos, int length, int initStyle, WordList *keywordlists[],

diff --git a/scintilla/lexers/LexHaskell.cxx b/scintilla/lexers/LexHaskell.cxx
index c4b1361..65fc5fe 100644
--- a/scintilla/lexers/LexHaskell.cxx
+++ b/scintilla/lexers/LexHaskell.cxx
@@ -40,40 +40,37 @@
 #include "CharacterSet.h"

 #include "LexerModule.h"

 #include "OptionSet.h"

+#include "CharacterCategory.h"

 

 #ifdef SCI_NAMESPACE

 using namespace Scintilla;

 #endif

 

-static int u_iswalpha(int);

-static int u_iswalnum(int);

-static int u_iswupper(int);

-static int u_IsHaskellSymbol(int);

+// See https://github.com/ghc/ghc/blob/master/compiler/parser/Lexer.x#L1682

+// Note, letter modifiers are prohibited.

 

-// #define HASKELL_UNICODE

-

-#ifndef HASKELL_UNICODE

-

-// Stubs

-

-static int u_iswalpha(int) {

-   return 0;

+static int u_iswupper (int ch) {

+   CharacterCategory c = CategoriseCharacter(ch);

+   return c == ccLu || c == ccLt;

 }

 

-static int u_iswalnum(int) {

-   return 0;

+static int u_iswalpha (int ch) {

+   CharacterCategory c = CategoriseCharacter(ch);

+   return c == ccLl || c == ccLu || c == ccLt || c == ccLo;

 }

 

-static int u_iswupper(int) {

-   return 0;

+static int u_iswalnum (int ch) {

+   CharacterCategory c = CategoriseCharacter(ch);

+   return c == ccLl || c == ccLu || c == ccLt || c == ccLo

+       || c == ccNd || c == ccNo;

 }

 

-static int u_IsHaskellSymbol(int) {

-   return 0;

+static int u_IsHaskellSymbol(int ch) {

+   CharacterCategory c = CategoriseCharacter(ch);

+   return c == ccPc || c == ccPd || c == ccPo

+       || c == ccSm || c == ccSc || c == ccSk || c == ccSo;

 }

 

-#endif

-

 static inline bool IsHaskellLetter(const int ch) {

    if (IsASCII(ch)) {

       return (ch >= 'a' && ch <= 'z')

@@ -597,7 +594,8 @@ void SCI_METHOD LexerHaskell::Lex(unsigned int startPos, int length, int initSty
          hs.lmode = LITERATE_BIRD;

       }

          // Preprocessor

-      else if (sc.atLineStart && sc.ch == '#' && options.cpp) {

+      else if (sc.atLineStart && sc.ch == '#' && options.cpp

+            && (!options.stylingWithinPreprocessor || sc.state == SCE_HA_DEFAULT)) {

          sc.SetState(SCE_HA_PREPROCESSOR);

          sc.Forward();

       }

@@ -960,7 +958,6 @@ void SCI_METHOD LexerHaskell::Lex(unsigned int startPos, int length, int initSty
          sc.Forward();

       }

    }

-   styler.SetLineState(lineCurrent, hs.ToLineState());

    sc.Complete();

 }

 

diff --git a/scintilla/lexers/LexLua.cxx b/scintilla/lexers/LexLua.cxx
index de9c41b..a571320 100644
--- a/scintilla/lexers/LexLua.cxx
+++ b/scintilla/lexers/LexLua.cxx
@@ -132,55 +132,38 @@ static void ColouriseLuaDoc(
 		if (sc.state == SCE_LUA_OPERATOR) {

 			if (sc.ch == ':' && sc.chPrev == ':') {	// :: <label> :: forward scan

 				sc.Forward();

-				int ln = 0, maxln = startPos + length - sc.currentPos;

-				int c;

-				while (ln < maxln) {		// determine line extent

-					c = sc.GetRelative(ln);

-					if (c == '\r' || c == '\n')

-						break;

-					ln++;

-				}

-				maxln = ln; ln = 0;

-				while (ln < maxln) {		// skip over spaces/tabs

-					if (!IsASpaceOrTab(sc.GetRelative(ln)))

-						break;

+				int ln = 0;

+				while (IsASpaceOrTab(sc.GetRelative(ln)))	// skip over spaces/tabs

 					ln++;

-				}

 				int ws1 = ln;

 				if (setWordStart.Contains(sc.GetRelative(ln))) {

-					int i = 0;

+					int c, i = 0;

 					char s[100];

-					while (ln < maxln) {	// get potential label

-						c = sc.GetRelative(ln);

-						if (!setWord.Contains(c))

-							break;

+					while (setWord.Contains(c = sc.GetRelative(ln))) {	// get potential label

 						if (i < 90)

 							s[i++] = c;

 						ln++;

 					}

 					s[i] = '\0'; int lbl = ln;

 					if (!keywords.InList(s)) {

-						while (ln < maxln) {		// skip over spaces/tabs

-							if (!IsASpaceOrTab(sc.GetRelative(ln)))

-								break;

+						while (IsASpaceOrTab(sc.GetRelative(ln)))	// skip over spaces/tabs

 							ln++;

-						}

 						int ws2 = ln - lbl;

 						if (sc.GetRelative(ln) == ':' && sc.GetRelative(ln + 1) == ':') {

 							// final :: found, complete valid label construct

 							sc.ChangeState(SCE_LUA_LABEL);

 							if (ws1) {

 								sc.SetState(SCE_LUA_DEFAULT);

-								sc.Forward(ws1);

+								sc.ForwardBytes(ws1);

 							}

 							sc.SetState(SCE_LUA_LABEL);

-							sc.Forward(lbl - ws1);

+							sc.ForwardBytes(lbl - ws1);

 							if (ws2) {

 								sc.SetState(SCE_LUA_DEFAULT);

-								sc.Forward(ws2);

+								sc.ForwardBytes(ws2);

 							}

 							sc.SetState(SCE_LUA_LABEL);

-							sc.Forward(2);

+							sc.ForwardBytes(2);

 						}

 					}

 				}

diff --git a/scintilla/lexers/LexOthers.cxx b/scintilla/lexers/LexOthers.cxx
index b887c53..bf37b16 100644
--- a/scintilla/lexers/LexOthers.cxx
+++ b/scintilla/lexers/LexOthers.cxx
@@ -922,8 +922,9 @@ static int RecogniseErrorListLine(const char *lineBuffer, unsigned int lengthLin
 	        (strstr(lineBuffer, " at ") < (lineBuffer + lengthLine)) &&

 	           strstr(lineBuffer, " line ") &&

 	           (strstr(lineBuffer, " line ") < (lineBuffer + lengthLine)) &&

-	        (strstr(lineBuffer, " at ") < (strstr(lineBuffer, " line ")))) {

-		// perl error message

+	        (strstr(lineBuffer, " at ") + 4 < (strstr(lineBuffer, " line ")))) {

+		// perl error message:

+		// <message> at <file> line <line>

 		return SCE_ERR_PERL;

 	} else if ((memcmp(lineBuffer, "   at ", 6) == 0) &&

 	           strstr(lineBuffer, ":line ")) {

diff --git a/scintilla/lexers/LexPerl.cxx b/scintilla/lexers/LexPerl.cxx
index 70aec18..fddb24e 100644
--- a/scintilla/lexers/LexPerl.cxx
+++ b/scintilla/lexers/LexPerl.cxx
@@ -188,22 +188,6 @@ static int styleCheckIdentifier(LexAccessor &styler, unsigned int bk) {
 	return 0;

 }

 

-static int inputsymbolScan(LexAccessor &styler, unsigned int pos, unsigned int endPos) {

-	// looks forward for matching > on same line; a bit ugly

-	unsigned int fw = pos;

-	while (++fw < endPos) {

-		int fwch = static_cast<unsigned char>(styler.SafeGetCharAt(fw));

-		if (fwch == '\r' || fwch == '\n') {

-			return 0;

-		} else if (fwch == '>') {

-			if (styler.Match(fw - 2, "<=>"))	// '<=>' case

-				return 0;

-			return fw - pos;

-		}

-	}

-	return 0;

-}

-

 static int podLineScan(LexAccessor &styler, unsigned int &pos, unsigned int endPos) {

 	// forward scan the current line to classify line for POD style

 	int state = -1;

@@ -398,6 +382,7 @@ public:
 	static ILexer *LexerFactoryPerl() {

 		return new LexerPerl();

 	}

+	int InputSymbolScan(StyleContext &sc);

 	void InterpolateSegment(StyleContext &sc, int maxSeg, bool isPattern=false);

 };

 

@@ -427,6 +412,21 @@ int SCI_METHOD LexerPerl::WordListSet(int n, const char *wl) {
 	return firstModification;

 }

 

+int LexerPerl::InputSymbolScan(StyleContext &sc) {

+	// forward scan for matching > on same line; file handles

+	int c, sLen = 0;

+	while ((c = sc.GetRelativeCharacter(++sLen)) != 0) {

+		if (c == '\r' || c == '\n') {

+			return 0;

+		} else if (c == '>') {

+			if (sc.Match("<=>"))	// '<=>' case

+				return 0;

+			return sLen;

+		}

+	}

+	return 0;

+}

+

 void LexerPerl::InterpolateSegment(StyleContext &sc, int maxSeg, bool isPattern) {

 	// interpolate a segment (with no active backslashes or delimiters within)

 	// switch in or out of an interpolation style or continue current style

@@ -441,39 +441,42 @@ void LexerPerl::InterpolateSegment(StyleContext &sc, int maxSeg, bool isPattern)
 			if (sc.ch == '$' && sc.chNext == '#') {	// starts with $#

 				sLen++;

 			}

-			while ((maxSeg > sLen) && (sc.GetRelative(sLen) == '$'))	// >0 $ dereference within

+			while ((maxSeg > sLen) && (sc.GetRelativeCharacter(sLen) == '$'))	// >0 $ dereference within

 				sLen++;

-			if ((maxSeg > sLen) && (sc.GetRelative(sLen) == '{')) {	// { start for {word}

+			if ((maxSeg > sLen) && (sc.GetRelativeCharacter(sLen) == '{')) {	// { start for {word}

 				sLen++;

 				braces = true;

 			}

 			if (maxSeg > sLen) {

-				int c = sc.GetRelative(sLen);

+				int c = sc.GetRelativeCharacter(sLen);

 				if (setWordStart.Contains(c)) {	// word (various)

 					sLen++;

 					isVar = true;

-					while ((maxSeg > sLen) && setWord.Contains(sc.GetRelative(sLen)))

+					while (maxSeg > sLen) {

+						if (!setWord.Contains(sc.GetRelativeCharacter(sLen)))

+							break;

 						sLen++;

+					}

 				} else if (braces && IsADigit(c) && (sLen == 2)) {	// digit for ${digit}

 					sLen++;

 					isVar = true;

 				}

 			}

 			if (braces) {

-				if ((maxSeg > sLen) && (sc.GetRelative(sLen) == '}')) {	// } end for {word}

+				if ((maxSeg > sLen) && (sc.GetRelativeCharacter(sLen) == '}')) {	// } end for {word}

 					sLen++;

 				} else

 					isVar = false;

 			}

 		}

 		if (!isVar && (maxSeg > 1)) {	// $- or @-specific variable patterns

-			sLen = 1;

 			int c = sc.chNext;

 			if (sc.ch == '$') {

+				sLen = 1;

 				if (IsADigit(c)) {	// $[0-9] and slurp trailing digits

 					sLen++;

 					isVar = true;

-					while ((maxSeg > sLen) && IsADigit(sc.GetRelative(sLen)))

+					while ((maxSeg > sLen) && IsADigit(sc.GetRelativeCharacter(sLen)))

 						sLen++;

 				} else if (setSpecialVar.Contains(c)) {	// $ special variables

 					sLen++;

@@ -483,12 +486,13 @@ void LexerPerl::InterpolateSegment(StyleContext &sc, int maxSeg, bool isPattern)
 					isVar = true;

 				} else if (c == '^') {	// $^A control-char style

 					sLen++;

-					if ((maxSeg > sLen) && setControlVar.Contains(sc.GetRelative(sLen))) {

+					if ((maxSeg > sLen) && setControlVar.Contains(sc.GetRelativeCharacter(sLen))) {

 						sLen++;

 						isVar = true;

 					}

 				}

 			} else if (sc.ch == '@') {

+				sLen = 1;

 				if (!isPattern && ((c == '+') || (c == '-'))) {	// @ specials non-pattern

 					sLen++;

 					isVar = true;

@@ -576,7 +580,7 @@ void SCI_METHOD LexerPerl::Lex(unsigned int startPos, int length, int initStyle,
 		int Count;

 		int Up, Down;

 		QuoteCls() {

-			this->New(1);

+			New(1);

 		}

 		void New(int r = 1) {

 			Rep   = r;

@@ -896,19 +900,18 @@ void SCI_METHOD LexerPerl::Lex(unsigned int startPos, int length, int initStyle,
 				break;

 			}

 			while (!sc.atLineEnd) {		// "EOF" and `EOF` interpolated

-				int s = 0, endType = 0;

-				int maxSeg = endPos - sc.currentPos;

-				while (s < maxSeg) {	// scan to break string into segments

-					int c = sc.GetRelative(s);

+				int c, sLen = 0, endType = 0;

+				while ((c = sc.GetRelativeCharacter(sLen)) != 0) {

+					// scan to break string into segments

 					if (c == '\\') {

 						endType = 1; break;

 					} else if (c == '\r' || c == '\n') {

 						endType = 2; break;

 					}

-					s++;

+					sLen++;

 				}

-				if (s > 0)	// process non-empty segments

-					InterpolateSegment(sc, s);

+				if (sLen > 0)	// process non-empty segments

+					InterpolateSegment(sc, sLen);

 				if (endType == 1) {

 					sc.Forward();

 					// \ at end-of-line does not appear to have any effect, skip

@@ -969,10 +972,9 @@ void SCI_METHOD LexerPerl::Lex(unsigned int startPos, int length, int initStyle,
 			} else if (!Quote.Up && !IsASpace(sc.ch)) {

 				Quote.Open(sc.ch);

 			} else {

-				int s = 0, endType = 0;

-				int maxSeg = endPos - sc.currentPos;

-				while (s < maxSeg) {	// scan to break string into segments

-					int c = sc.GetRelative(s);

+				int c, sLen = 0, endType = 0;

+				while ((c = sc.GetRelativeCharacter(sLen)) != 0) {

+					// scan to break string into segments

 					if (IsASpace(c)) {

 						break;

 					} else if (c == '\\' && Quote.Up != '\\') {

@@ -985,13 +987,13 @@ void SCI_METHOD LexerPerl::Lex(unsigned int startPos, int length, int initStyle,
 						}

 					} else if (c == Quote.Up)

 						Quote.Count++;

-					s++;

+					sLen++;

 				}

-				if (s > 0) {	// process non-empty segments

+				if (sLen > 0) {	// process non-empty segments

 					if (Quote.Up != '\'') {

-						InterpolateSegment(sc, s, true);

+						InterpolateSegment(sc, sLen, true);

 					} else		// non-interpolated path

-						sc.Forward(s);

+						sc.Forward(sLen);

 				}

 				if (endType == 1)

 					sc.Forward();

@@ -1005,11 +1007,10 @@ void SCI_METHOD LexerPerl::Lex(unsigned int startPos, int length, int initStyle,
 			} else if (!Quote.Up && !IsASpace(sc.ch)) {

 				Quote.Open(sc.ch);

 			} else {

-				int s = 0, endType = 0;

-				int maxSeg = endPos - sc.currentPos;

+				int c, sLen = 0, endType = 0;

 				bool isPattern = (Quote.Rep == 2);

-				while (s < maxSeg) {	// scan to break string into segments

-					int c = sc.GetRelative(s);

+				while ((c = sc.GetRelativeCharacter(sLen)) != 0) {

+					// scan to break string into segments

 					if (c == '\\' && Quote.Up != '\\') {

 						endType = 2; break;

 					} else if (Quote.Count == 0 && Quote.Rep == 1) {

@@ -1020,7 +1021,7 @@ void SCI_METHOD LexerPerl::Lex(unsigned int startPos, int length, int initStyle,
 						// For '#', if no whitespace in between, it's a delimiter.

 						if (IsASpace(c)) {

 							// Keep going

-						} else if (c == '#' && IsASpaceOrTab(sc.GetRelative(s - 1))) {

+						} else if (c == '#' && IsASpaceOrTab(sc.GetRelative(sLen - 1))) {

 							endType = 3;

 						} else

 							Quote.Open(c);

@@ -1039,13 +1040,13 @@ void SCI_METHOD LexerPerl::Lex(unsigned int startPos, int length, int initStyle,
 						Quote.Count++;

 					} else if (IsASpace(c))

 						break;

-					s++;

+					sLen++;

 				}

-				if (s > 0) {	// process non-empty segments

+				if (sLen > 0) {	// process non-empty segments

 					if (sc.state == SCE_PL_REGSUBST && Quote.Up != '\'') {

-						InterpolateSegment(sc, s, isPattern);

+						InterpolateSegment(sc, sLen, isPattern);

 					} else		// non-interpolated path

-						sc.Forward(s);

+						sc.Forward(sLen);

 				}

 				if (endType == 2) {

 					sc.Forward();

@@ -1063,10 +1064,9 @@ void SCI_METHOD LexerPerl::Lex(unsigned int startPos, int length, int initStyle,
 			if (!Quote.Down && !IsASpace(sc.ch)) {

 				Quote.Open(sc.ch);

 			} else {

-				int s = 0, endType = 0;

-				int maxSeg = endPos - sc.currentPos;

-				while (s < maxSeg) {	// scan to break string into segments

-					int c = sc.GetRelative(s);

+				int c, sLen = 0, endType = 0;

+				while ((c = sc.GetRelativeCharacter(sLen)) != 0) {

+					// scan to break string into segments

 					if (IsASpace(c)) {

 						break;

 					} else if (c == '\\' && Quote.Up != '\\') {

@@ -1078,23 +1078,23 @@ void SCI_METHOD LexerPerl::Lex(unsigned int startPos, int length, int initStyle,
 						}

 					} else if (c == Quote.Up)

 						Quote.Count++;

-					s++;

+					sLen++;

 				}

-				if (s > 0) {	// process non-empty segments

+				if (sLen > 0) {	// process non-empty segments

 					switch (sc.state) {

 					case SCE_PL_STRING:

 					case SCE_PL_STRING_QQ:

 					case SCE_PL_BACKTICKS:

-						InterpolateSegment(sc, s);

+						InterpolateSegment(sc, sLen);

 						break;

 					case SCE_PL_STRING_QX:

 						if (Quote.Up != '\'') {

-							InterpolateSegment(sc, s);

+							InterpolateSegment(sc, sLen);

 							break;

 						}

 						// (continued for ' delim)

 					default:	// non-interpolated path

-						sc.Forward(s);

+						sc.Forward(sLen);

 					}

 				}

 				if (endType == 2) {

@@ -1474,7 +1474,7 @@ void SCI_METHOD LexerPerl::Lex(unsigned int startPos, int length, int initStyle,
 				} else if (sc.ch == '<') {	// handle '<', inputsymbol

 					if (preferRE) {

 						// forward scan

-						int i = inputsymbolScan(styler, sc.currentPos, endPos);

+						int i = InputSymbolScan(sc);

 						if (i > 0) {

 							sc.SetState(SCE_PL_IDENTIFIER);

 							sc.Forward(i);

diff --git a/scintilla/lexers/LexRuby.cxx b/scintilla/lexers/LexRuby.cxx
index b83569c..32b8433 100644
--- a/scintilla/lexers/LexRuby.cxx
+++ b/scintilla/lexers/LexRuby.cxx
@@ -254,7 +254,7 @@ class QuoteCls {
     char Up;

     char Down;

     QuoteCls() {

-        this->New();

+        New();

     }

     void New() {

         Count = 0;

diff --git a/scintilla/lexlib/CharacterCategory.cxx b/scintilla/lexlib/CharacterCategory.cxx
new file mode 100644
index 0000000..a837760
--- /dev/null
+++ b/scintilla/lexlib/CharacterCategory.cxx
@@ -0,0 +1,3303 @@
+// Scintilla source code edit control
+/** @file CharacterCategory.cxx
+ ** Returns the Unicode general category of a character.
+ ** Table automatically regenerated by scripts/GenerateCharacterCategory.py
+ ** Should only be rarely regenerated for new versions of Unicode.
+ **/
+// Copyright 2013 by Neil Hodgson <neilh@scintilla.org>
+// The License.txt file describes the conditions under which this software may be distributed.
+
+#include <algorithm>
+
+#include "CharacterCategory.h"
+
+#ifdef SCI_NAMESPACE
+namespace Scintilla {
+#endif
+
+namespace {
+	// Use an unnamed namespace to protect the declarations from name conflicts
+
+const int catRanges[] = {
+//++Autogenerated -- start of section automatically generated
+// Created with Python 3.3.0,  Unicode 6.1.0
+25,
+1046,
+1073,
+1171,
+1201,
+1293,
+1326,
+1361,
+1394,
+1425,
+1452,
+1489,
+1544,
+1873,
+1938,
+2033,
+2080,
+2925,
+2961,
+2990,
+3028,
+3051,
+3092,
+3105,
+3949,
+3986,
+4014,
+4050,
+4089,
+5142,
+5169,
+5203,
+5333,
+5361,
+5396,
+5429,
+5444,
+5487,
+5522,
+5562,
+5589,
+5620,
+5653,
+5682,
+5706,
+5780,
+5793,
+5841,
+5908,
+5930,
+5956,
+6000,
+6026,
+6129,
+6144,
+6898,
+6912,
+7137,
+7922,
+7937,
+8192,
+8225,
+8256,
+8289,
+8320,
+8353,
+8384,
+8417,
+8448,
+8481,
+8512,
+8545,
+8576,
+8609,
+8640,
+8673,
+8704,
+8737,
+8768,
+8801,
+8832,
+8865,
+8896,
+8929,
+8960,
+8993,
+9024,
+9057,
+9088,
+9121,
+9152,
+9185,
+9216,
+9249,
+9280,
+9313,
+9344,
+9377,
+9408,
+9441,
+9472,
+9505,
+9536,
+9569,
+9600,
+9633,
+9664,
+9697,
+9728,
+9761,
+9792,
+9825,
+9856,
+9889,
+9920,
+9953,
+10016,
+10049,
+10080,
+10113,
+10144,
+10177,
+10208,
+10241,
+10272,
+10305,
+10336,
+10369,
+10400,
+10433,
+10464,
+10497,
+10560,
+10593,
+10624,
+10657,
+10688,
+10721,
+10752,
+10785,
+10816,
+10849,
+10880,
+10913,
+10944,
+10977,
+11008,
+11041,
+11072,
+11105,
+11136,
+11169,
+11200,
+11233,
+11264,
+11297,
+11328,
+11361,
+11392,
+11425,
+11456,
+11489,
+11520,
+11553,
+11584,
+11617,
+11648,
+11681,
+11712,
+11745,
+11776,
+11809,
+11840,
+11873,
+11904,
+11937,
+11968,
+12001,
+12032,
+12097,
+12128,
+12161,
+12192,
+12225,
+12320,
+12385,
+12416,
+12449,
+12480,
+12545,
+12576,
+12673,
+12736,
+12865,
+12896,
+12961,
+12992,
+13089,
+13184,
+13249,
+13280,
+13345,
+13376,
+13409,
+13440,
+13473,
+13504,
+13569,
+13600,
+13633,
+13696,
+13729,
+13760,
+13825,
+13856,
+13953,
+13984,
+14017,
+14048,
+14113,
+14180,
+14208,
+14241,
+14340,
+14464,
+14498,
+14529,
+14560,
+14594,
+14625,
+14656,
+14690,
+14721,
+14752,
+14785,
+14816,
+14849,
+14880,
+14913,
+14944,
+14977,
+15008,
+15041,
+15072,
+15105,
+15136,
+15169,
+15200,
+15233,
+15296,
+15329,
+15360,
+15393,
+15424,
+15457,
+15488,
+15521,
+15552,
+15585,
+15616,
+15649,
+15680,
+15713,
+15744,
+15777,
+15808,
+15841,
+15904,
+15938,
+15969,
+16000,
+16033,
+16064,
+16161,
+16192,
+16225,
+16256,
+16289,
+16320,
+16353,
+16384,
+16417,
+16448,
+16481,
+16512,
+16545,
+16576,
+16609,
+16640,
+16673,
+16704,
+16737,
+16768,
+16801,
+16832,
+16865,
+16896,
+16929,
+16960,
+16993,
+17024,
+17057,
+17088,
+17121,
+17152,
+17185,
+17216,
+17249,
+17280,
+17313,
+17344,
+17377,
+17408,
+17441,
+17472,
+17505,
+17536,
+17569,
+17600,
+17633,
+17664,
+17697,
+17728,
+17761,
+17792,
+17825,
+17856,
+17889,
+17920,
+17953,
+17984,
+18017,
+18240,
+18305,
+18336,
+18401,
+18464,
+18497,
+18528,
+18657,
+18688,
+18721,
+18752,
+18785,
+18816,
+18849,
+18880,
+18913,
+21124,
+21153,
+22019,
+22612,
+22723,
+23124,
+23555,
+23732,
+23939,
+23988,
+24003,
+24052,
+24581,
+28160,
+28193,
+28224,
+28257,
+28291,
+28340,
+28352,
+28385,
+28445,
+28483,
+28513,
+28625,
+28669,
+28820,
+28864,
+28913,
+28928,
+29053,
+29056,
+29117,
+29120,
+29185,
+29216,
+29789,
+29792,
+30081,
+31200,
+31233,
+31296,
+31393,
+31488,
+31521,
+31552,
+31585,
+31616,
+31649,
+31680,
+31713,
+31744,
+31777,
+31808,
+31841,
+31872,
+31905,
+31936,
+31969,
+32000,
+32033,
+32064,
+32097,
+32128,
+32161,
+32192,
+32225,
+32384,
+32417,
+32466,
+32480,
+32513,
+32544,
+32609,
+32672,
+34305,
+35840,
+35873,
+35904,
+35937,
+35968,
+36001,
+36032,
+36065,
+36096,
+36129,
+36160,
+36193,
+36224,
+36257,
+36288,
+36321,
+36352,
+36385,
+36416,
+36449,
+36480,
+36513,
+36544,
+36577,
+36608,
+36641,
+36672,
+36705,
+36736,
+36769,
+36800,
+36833,
+36864,
+36897,
+36949,
+36965,
+37127,
+37184,
+37217,
+37248,
+37281,
+37312,
+37345,
+37376,
+37409,
+37440,
+37473,
+37504,
+37537,
+37568,
+37601,
+37632,
+37665,
+37696,
+37729,
+37760,
+37793,
+37824,
+37857,
+37888,
+37921,
+37952,
+37985,
+38016,
+38049,
+38080,
+38113,
+38144,
+38177,
+38208,
+38241,
+38272,
+38305,
+38336,
+38369,
+38400,
+38433,
+38464,
+38497,
+38528,
+38561,
+38592,
+38625,
+38656,
+38689,
+38720,
+38753,
+38784,
+38817,
+38848,
+38881,
+38912,
+38977,
+39008,
+39041,
+39072,
+39105,
+39136,
+39169,
+39200,
+39233,
+39264,
+39297,
+39328,
+39361,
+39424,
+39457,
+39488,
+39521,
+39552,
+39585,
+39616,
+39649,
+39680,
+39713,
+39744,
+39777,
+39808,
+39841,
+39872,
+39905,
+39936,
+39969,
+40000,
+40033,
+40064,
+40097,
+40128,
+40161,
+40192,
+40225,
+40256,
+40289,
+40320,
+40353,
+40384,
+40417,
+40448,
+40481,
+40512,
+40545,
+40576,
+40609,
+40640,
+40673,
+40704,
+40737,
+40768,
+40801,
+40832,
+40865,
+40896,
+40929,
+40960,
+40993,
+41024,
+41057,
+41088,
+41121,
+41152,
+41185,
+41216,
+41249,
+41280,
+41313,
+41344,
+41377,
+41408,
+41441,
+41472,
+41505,
+41536,
+41569,
+41600,
+41633,
+41664,
+41697,
+41728,
+41761,
+41792,
+41825,
+41856,
+41889,
+41920,
+41953,
+41984,
+42017,
+42048,
+42081,
+42112,
+42145,
+42176,
+42209,
+42269,
+42528,
+43773,
+43811,
+43857,
+44061,
+44065,
+45341,
+45361,
+45388,
+45437,
+45555,
+45597,
+45605,
+47052,
+47077,
+47121,
+47141,
+47217,
+47237,
+47313,
+47333,
+47389,
+47620,
+48509,
+48644,
+48753,
+48829,
+49178,
+49341,
+49362,
+49457,
+49523,
+49553,
+49621,
+49669,
+50033,
+50077,
+50129,
+50180,
+51203,
+51236,
+51557,
+52232,
+52561,
+52676,
+52741,
+52772,
+55953,
+55972,
+56005,
+56250,
+56277,
+56293,
+56483,
+56549,
+56629,
+56645,
+56772,
+56840,
+57156,
+57269,
+57316,
+57361,
+57821,
+57850,
+57860,
+57893,
+57924,
+58885,
+59773,
+59812,
+62661,
+63012,
+63069,
+63496,
+63812,
+64869,
+65155,
+65237,
+65265,
+65347,
+65405,
+65540,
+66245,
+66371,
+66405,
+66691,
+66725,
+66819,
+66853,
+67037,
+67089,
+67581,
+67588,
+68389,
+68509,
+68561,
+68605,
+70660,
+70717,
+70724,
+71101,
+72837,
+73725,
+73733,
+73830,
+73860,
+75589,
+75622,
+75653,
+75684,
+75718,
+75813,
+76070,
+76197,
+76230,
+76292,
+76325,
+76548,
+76869,
+76945,
+77000,
+77329,
+77347,
+77380,
+77597,
+77604,
+77853,
+77861,
+77894,
+77981,
+77988,
+78269,
+78308,
+78397,
+78436,
+79165,
+79172,
+79421,
+79428,
+79485,
+79556,
+79709,
+79749,
+79780,
+79814,
+79909,
+80061,
+80102,
+80189,
+80230,
+80293,
+80324,
+80381,
+80614,
+80669,
+80772,
+80861,
+80868,
+80965,
+81053,
+81096,
+81412,
+81491,
+81546,
+81749,
+81779,
+81821,
+81957,
+82022,
+82077,
+82084,
+82301,
+82404,
+82493,
+82532,
+83261,
+83268,
+83517,
+83524,
+83613,
+83620,
+83709,
+83716,
+83805,
+83845,
+83901,
+83910,
+84005,
+84093,
+84197,
+84285,
+84325,
+84445,
+84517,
+84573,
+84772,
+84925,
+84932,
+84989,
+85192,
+85509,
+85572,
+85669,
+85725,
+86053,
+86118,
+86173,
+86180,
+86493,
+86500,
+86621,
+86628,
+87357,
+87364,
+87613,
+87620,
+87709,
+87716,
+87901,
+87941,
+87972,
+88006,
+88101,
+88285,
+88293,
+88358,
+88413,
+88422,
+88485,
+88541,
+88580,
+88637,
+89092,
+89157,
+89245,
+89288,
+89617,
+89651,
+89693,
+90149,
+90182,
+90269,
+90276,
+90557,
+90596,
+90685,
+90724,
+91453,
+91460,
+91709,
+91716,
+91805,
+91812,
+91997,
+92037,
+92068,
+92102,
+92133,
+92166,
+92197,
+92349,
+92390,
+92477,
+92518,
+92581,
+92637,
+92869,
+92902,
+92957,
+93060,
+93149,
+93156,
+93253,
+93341,
+93384,
+93717,
+93732,
+93770,
+93981,
+94277,
+94308,
+94365,
+94372,
+94589,
+94660,
+94781,
+94788,
+94941,
+95012,
+95101,
+95108,
+95165,
+95172,
+95261,
+95332,
+95421,
+95492,
+95613,
+95684,
+96093,
+96198,
+96261,
+96294,
+96381,
+96454,
+96573,
+96582,
+96677,
+96733,
+96772,
+96829,
+96998,
+97053,
+97480,
+97802,
+97909,
+98099,
+98133,
+98173,
+98342,
+98461,
+98468,
+98749,
+98756,
+98877,
+98884,
+99645,
+99652,
+99997,
+100004,
+100189,
+100260,
+100293,
+100390,
+100541,
+100549,
+100669,
+100677,
+100829,
+101029,
+101117,
+101124,
+101213,
+101380,
+101445,
+101533,
+101576,
+101917,
+102154,
+102389,
+102429,
+102470,
+102557,
+102564,
+102845,
+102852,
+102973,
+102980,
+103741,
+103748,
+104093,
+104100,
+104285,
+104325,
+104356,
+104390,
+104421,
+104454,
+104637,
+104645,
+104678,
+104765,
+104774,
+104837,
+104925,
+105126,
+105213,
+105412,
+105469,
+105476,
+105541,
+105629,
+105672,
+106013,
+106020,
+106109,
+106566,
+106653,
+106660,
+106941,
+106948,
+107069,
+107076,
+108413,
+108452,
+108486,
+108581,
+108733,
+108742,
+108861,
+108870,
+108965,
+108996,
+109053,
+109286,
+109341,
+109572,
+109637,
+109725,
+109768,
+110090,
+110301,
+110389,
+110404,
+110621,
+110662,
+110749,
+110756,
+111357,
+111428,
+112221,
+112228,
+112541,
+112548,
+112605,
+112644,
+112893,
+112965,
+113021,
+113126,
+113221,
+113341,
+113349,
+113405,
+113414,
+113693,
+114246,
+114321,
+114365,
+114724,
+116261,
+116292,
+116357,
+116605,
+116723,
+116740,
+116931,
+116965,
+117233,
+117256,
+117585,
+117661,
+118820,
+118909,
+118916,
+118973,
+119012,
+119101,
+119108,
+119165,
+119204,
+119261,
+119428,
+119581,
+119588,
+119837,
+119844,
+119965,
+119972,
+120029,
+120036,
+120093,
+120132,
+120221,
+120228,
+120357,
+120388,
+120453,
+120669,
+120677,
+120740,
+120797,
+120836,
+121021,
+121027,
+121085,
+121093,
+121309,
+121352,
+121693,
+121732,
+121885,
+122884,
+122933,
+123025,
+123509,
+123537,
+123573,
+123653,
+123733,
+123912,
+124234,
+124565,
+124581,
+124629,
+124645,
+124693,
+124709,
+124749,
+124782,
+124813,
+124846,
+124870,
+124932,
+125213,
+125220,
+126397,
+126501,
+126950,
+126981,
+127153,
+127173,
+127236,
+127397,
+127773,
+127781,
+128957,
+128981,
+129221,
+129269,
+129469,
+129493,
+129553,
+129717,
+129841,
+129917,
+131076,
+132454,
+132517,
+132646,
+132677,
+132870,
+132901,
+132966,
+133029,
+133092,
+133128,
+133457,
+133636,
+133830,
+133893,
+133956,
+134085,
+134180,
+134214,
+134308,
+134374,
+134596,
+134693,
+134820,
+135237,
+135270,
+135333,
+135398,
+135589,
+135620,
+135654,
+135688,
+136006,
+136101,
+136149,
+136192,
+137437,
+137440,
+137501,
+137632,
+137693,
+137732,
+139121,
+139139,
+139172,
+149821,
+149828,
+149981,
+150020,
+150269,
+150276,
+150333,
+150340,
+150493,
+150532,
+151869,
+151876,
+152029,
+152068,
+153149,
+153156,
+153309,
+153348,
+153597,
+153604,
+153661,
+153668,
+153821,
+153860,
+154365,
+154372,
+156221,
+156228,
+156381,
+156420,
+158589,
+158629,
+158737,
+159018,
+159677,
+159748,
+160277,
+160605,
+160772,
+163517,
+163852,
+163876,
+183729,
+183780,
+184342,
+184356,
+185197,
+185230,
+185277,
+185348,
+187761,
+187849,
+187965,
+188420,
+188861,
+188868,
+188997,
+189117,
+189444,
+190021,
+190129,
+190205,
+190468,
+191045,
+191133,
+191492,
+191933,
+191940,
+192061,
+192069,
+192157,
+192516,
+194181,
+194246,
+194277,
+194502,
+194757,
+194790,
+194853,
+195217,
+195299,
+195345,
+195443,
+195460,
+195493,
+195549,
+195592,
+195933,
+196106,
+196445,
+196625,
+196812,
+196849,
+196965,
+197078,
+197117,
+197128,
+197469,
+197636,
+198755,
+198788,
+200477,
+200708,
+202021,
+202052,
+202109,
+202244,
+204509,
+204804,
+205757,
+205829,
+205926,
+206053,
+206118,
+206237,
+206342,
+206405,
+206438,
+206629,
+206749,
+206869,
+206909,
+206993,
+207048,
+207364,
+208349,
+208388,
+208573,
+208900,
+210333,
+210438,
+210980,
+211206,
+211293,
+211464,
+211786,
+211837,
+211925,
+212996,
+213733,
+213798,
+213917,
+213969,
+214020,
+215718,
+215749,
+215782,
+215813,
+216061,
+216069,
+216102,
+216133,
+216166,
+216229,
+216486,
+216677,
+217021,
+217061,
+217096,
+217437,
+217608,
+217949,
+218129,
+218339,
+218385,
+218589,
+221189,
+221318,
+221348,
+222853,
+222886,
+222917,
+223078,
+223109,
+223142,
+223301,
+223334,
+223396,
+223645,
+223752,
+224081,
+224309,
+224613,
+224917,
+225213,
+225285,
+225350,
+225380,
+226342,
+226373,
+226502,
+226565,
+226630,
+226661,
+226694,
+226756,
+226824,
+227140,
+228549,
+228582,
+228613,
+228678,
+228773,
+228806,
+228837,
+228934,
+229021,
+229265,
+229380,
+230534,
+230789,
+231046,
+231109,
+231197,
+231281,
+231432,
+231773,
+231844,
+231944,
+232260,
+233219,
+233425,
+233501,
+235537,
+235805,
+236037,
+236145,
+236165,
+236582,
+236613,
+236836,
+236965,
+236996,
+237126,
+237189,
+237220,
+237309,
+237569,
+238979,
+240993,
+241411,
+241441,
+242531,
+243717,
+244989,
+245637,
+245760,
+245793,
+245824,
+245857,
+245888,
+245921,
+245952,
+245985,
+246016,
+246049,
+246080,
+246113,
+246144,
+246177,
+246208,
+246241,
+246272,
+246305,
+246336,
+246369,
+246400,
+246433,
+246464,
+246497,
+246528,
+246561,
+246592,
+246625,
+246656,
+246689,
+246720,
+246753,
+246784,
+246817,
+246848,
+246881,
+246912,
+246945,
+246976,
+247009,
+247040,
+247073,
+247104,
+247137,
+247168,
+247201,
+247232,
+247265,
+247296,
+247329,
+247360,
+247393,
+247424,
+247457,
+247488,
+247521,
+247552,
+247585,
+247616,
+247649,
+247680,
+247713,
+247744,
+247777,
+247808,
+247841,
+247872,
+247905,
+247936,
+247969,
+248000,
+248033,
+248064,
+248097,
+248128,
+248161,
+248192,
+248225,
+248256,
+248289,
+248320,
+248353,
+248384,
+248417,
+248448,
+248481,
+248512,
+248545,
+248576,
+248609,
+248640,
+248673,
+248704,
+248737,
+248768,
+248801,
+248832,
+248865,
+248896,
+248929,
+248960,
+248993,
+249024,
+249057,
+249088,
+249121,
+249152,
+249185,
+249216,
+249249,
+249280,
+249313,
+249344,
+249377,
+249408,
+249441,
+249472,
+249505,
+249536,
+249569,
+249600,
+249633,
+249664,
+249697,
+249728,
+249761,
+249792,
+249825,
+249856,
+249889,
+249920,
+249953,
+249984,
+250017,
+250048,
+250081,
+250112,
+250145,
+250176,
+250209,
+250240,
+250273,
+250304,
+250337,
+250368,
+250401,
+250432,
+250465,
+250496,
+250529,
+250816,
+250849,
+250880,
+250913,
+250944,
+250977,
+251008,
+251041,
+251072,
+251105,
+251136,
+251169,
+251200,
+251233,
+251264,
+251297,
+251328,
+251361,
+251392,
+251425,
+251456,
+251489,
+251520,
+251553,
+251584,
+251617,
+251648,
+251681,
+251712,
+251745,
+251776,
+251809,
+251840,
+251873,
+251904,
+251937,
+251968,
+252001,
+252032,
+252065,
+252096,
+252129,
+252160,
+252193,
+252224,
+252257,
+252288,
+252321,
+252352,
+252385,
+252416,
+252449,
+252480,
+252513,
+252544,
+252577,
+252608,
+252641,
+252672,
+252705,
+252736,
+252769,
+252800,
+252833,
+252864,
+252897,
+252928,
+252961,
+252992,
+253025,
+253056,
+253089,
+253120,
+253153,
+253184,
+253217,
+253248,
+253281,
+253312,
+253345,
+253376,
+253409,
+253440,
+253473,
+253504,
+253537,
+253568,
+253601,
+253632,
+253665,
+253696,
+253729,
+253760,
+253793,
+253824,
+253857,
+253888,
+253921,
+254208,
+254465,
+254685,
+254720,
+254941,
+254977,
+255232,
+255489,
+255744,
+256001,
+256221,
+256256,
+256477,
+256513,
+256797,
+256800,
+256861,
+256864,
+256925,
+256928,
+256989,
+256992,
+257025,
+257280,
+257537,
+258013,
+258049,
+258306,
+258561,
+258818,
+259073,
+259330,
+259585,
+259773,
+259777,
+259840,
+259970,
+260020,
+260033,
+260084,
+260161,
+260285,
+260289,
+260352,
+260482,
+260532,
+260609,
+260765,
+260801,
+260864,
+261021,
+261044,
+261121,
+261376,
+261556,
+261661,
+261697,
+261821,
+261825,
+261888,
+262018,
+262068,
+262141,
+262166,
+262522,
+262668,
+262865,
+262927,
+262960,
+262989,
+263023,
+263088,
+263117,
+263151,
+263185,
+263447,
+263480,
+263514,
+263670,
+263697,
+263983,
+264016,
+264049,
+264171,
+264241,
+264338,
+264365,
+264398,
+264433,
+264786,
+264817,
+264843,
+264881,
+265206,
+265242,
+265405,
+265562,
+265738,
+265763,
+265821,
+265866,
+266066,
+266157,
+266190,
+266211,
+266250,
+266578,
+266669,
+266702,
+266749,
+266755,
+267197,
+267283,
+268125,
+268805,
+269223,
+269349,
+269383,
+269477,
+269885,
+270357,
+270400,
+270453,
+270560,
+270613,
+270657,
+270688,
+270785,
+270848,
+270945,
+270997,
+271008,
+271061,
+271122,
+271136,
+271317,
+271488,
+271541,
+271552,
+271605,
+271616,
+271669,
+271680,
+271829,
+271841,
+271872,
+272001,
+272036,
+272161,
+272213,
+272257,
+272320,
+272402,
+272544,
+272577,
+272725,
+272754,
+272789,
+272833,
+272885,
+272906,
+273417,
+274528,
+274561,
+274601,
+274730,
+274781,
+274962,
+275125,
+275282,
+275349,
+275474,
+275509,
+275570,
+275605,
+275666,
+275701,
+275922,
+275957,
+276946,
+277013,
+277074,
+277109,
+277138,
+277173,
+278162,
+286741,
+286994,
+287125,
+287762,
+287829,
+288045,
+288078,
+288117,
+290706,
+290741,
+291698,
+292501,
+293778,
+293973,
+294557,
+294933,
+296189,
+296981,
+297341,
+297994,
+299925,
+302410,
+303125,
+308978,
+309013,
+309298,
+309333,
+311058,
+311317,
+314866,
+314901,
+319517,
+319541,
+322829,
+322862,
+322893,
+322926,
+322957,
+322990,
+323021,
+323054,
+323085,
+323118,
+323149,
+323182,
+323213,
+323246,
+323274,
+324245,
+325650,
+325805,
+325838,
+325874,
+326861,
+326894,
+326925,
+326958,
+326989,
+327022,
+327053,
+327086,
+327117,
+327150,
+327186,
+327701,
+335890,
+340077,
+340110,
+340141,
+340174,
+340205,
+340238,
+340269,
+340302,
+340333,
+340366,
+340397,
+340430,
+340461,
+340494,
+340525,
+340558,
+340589,
+340622,
+340653,
+340686,
+340717,
+340750,
+340786,
+342797,
+342830,
+342861,
+342894,
+342930,
+343949,
+343982,
+344018,
+352277,
+353810,
+354485,
+354546,
+354749,
+354837,
+355165,
+360448,
+361981,
+361985,
+363517,
+363520,
+363553,
+363584,
+363681,
+363744,
+363777,
+363808,
+363841,
+363872,
+363905,
+363936,
+364065,
+364096,
+364129,
+364192,
+364225,
+364419,
+364480,
+364577,
+364608,
+364641,
+364672,
+364705,
+364736,
+364769,
+364800,
+364833,
+364864,
+364897,
+364928,
+364961,
+364992,
+365025,
+365056,
+365089,
+365120,
+365153,
+365184,
+365217,
+365248,
+365281,
+365312,
+365345,
+365376,
+365409,
+365440,
+365473,
+365504,
+365537,
+365568,
+365601,
+365632,
+365665,
+365696,
+365729,
+365760,
+365793,
+365824,
+365857,
+365888,
+365921,
+365952,
+365985,
+366016,
+366049,
+366080,
+366113,
+366144,
+366177,
+366208,
+366241,
+366272,
+366305,
+366336,
+366369,
+366400,
+366433,
+366464,
+366497,
+366528,
+366561,
+366592,
+366625,
+366656,
+366689,
+366720,
+366753,
+366784,
+366817,
+366848,
+366881,
+366912,
+366945,
+366976,
+367009,
+367040,
+367073,
+367104,
+367137,
+367168,
+367201,
+367232,
+367265,
+367296,
+367329,
+367360,
+367393,
+367424,
+367457,
+367488,
+367521,
+367552,
+367585,
+367616,
+367649,
+367680,
+367713,
+367797,
+367968,
+368001,
+368032,
+368065,
+368101,
+368192,
+368225,
+368285,
+368433,
+368554,
+368593,
+368641,
+369885,
+369889,
+369949,
+370081,
+370141,
+370180,
+371997,
+372195,
+372241,
+372285,
+372709,
+372740,
+373501,
+373764,
+374013,
+374020,
+374269,
+374276,
+374525,
+374532,
+374781,
+374788,
+375037,
+375044,
+375293,
+375300,
+375549,
+375556,
+375805,
+375813,
+376849,
+376911,
+376944,
+376975,
+377008,
+377041,
+377135,
+377168,
+377201,
+377231,
+377264,
+377297,
+377580,
+377617,
+377676,
+377713,
+377743,
+377776,
+377809,
+377871,
+377904,
+377933,
+377966,
+377997,
+378030,
+378061,
+378094,
+378125,
+378158,
+378193,
+378339,
+378385,
+378700,
+378781,
+380949,
+381789,
+381813,
+384669,
+385045,
+391901,
+392725,
+393117,
+393238,
+393265,
+393365,
+393379,
+393412,
+393449,
+393485,
+393518,
+393549,
+393582,
+393613,
+393646,
+393677,
+393710,
+393741,
+393774,
+393813,
+393869,
+393902,
+393933,
+393966,
+393997,
+394030,
+394061,
+394094,
+394124,
+394157,
+394190,
+394261,
+394281,
+394565,
+394694,
+394764,
+394787,
+394965,
+395017,
+395107,
+395140,
+395185,
+395221,
+395293,
+395300,
+398077,
+398117,
+398196,
+398243,
+398308,
+398348,
+398372,
+401265,
+401283,
+401380,
+401437,
+401572,
+402909,
+402980,
+406013,
+406037,
+406090,
+406229,
+406532,
+407421,
+407573,
+408733,
+409092,
+409621,
+410621,
+410634,
+410965,
+411914,
+412181,
+412202,
+412693,
+413706,
+414037,
+415274,
+415765,
+417789,
+417813,
+425988,
+636637,
+636949,
+638980,
+1309117,
+1310724,
+1311395,
+1311428,
+1348029,
+1348117,
+1349885,
+1350148,
+1351427,
+1351633,
+1351684,
+1360259,
+1360305,
+1360388,
+1360904,
+1361220,
+1361309,
+1361920,
+1361953,
+1361984,
+1362017,
+1362048,
+1362081,
+1362112,
+1362145,
+1362176,
+1362209,
+1362240,
+1362273,
+1362304,
+1362337,
+1362368,
+1362401,
+1362432,
+1362465,
+1362496,
+1362529,
+1362560,
+1362593,
+1362624,
+1362657,
+1362688,
+1362721,
+1362752,
+1362785,
+1362816,
+1362849,
+1362880,
+1362913,
+1362944,
+1362977,
+1363008,
+1363041,
+1363072,
+1363105,
+1363136,
+1363169,
+1363200,
+1363233,
+1363264,
+1363297,
+1363328,
+1363361,
+1363396,
+1363429,
+1363463,
+1363569,
+1363589,
+1363921,
+1363939,
+1363968,
+1364001,
+1364032,
+1364065,
+1364096,
+1364129,
+1364160,
+1364193,
+1364224,
+1364257,
+1364288,
+1364321,
+1364352,
+1364385,
+1364416,
+1364449,
+1364480,
+1364513,
+1364544,
+1364577,
+1364608,
+1364641,
+1364672,
+1364705,
+1364765,
+1364965,
+1364996,
+1367241,
+1367557,
+1367633,
+1367837,
+1368084,
+1368803,
+1369108,
+1369152,
+1369185,
+1369216,
+1369249,
+1369280,
+1369313,
+1369344,
+1369377,
+1369408,
+1369441,
+1369472,
+1369505,
+1369536,
+1369569,
+1369664,
+1369697,
+1369728,
+1369761,
+1369792,
+1369825,
+1369856,
+1369889,
+1369920,
+1369953,
+1369984,
+1370017,
+1370048,
+1370081,
+1370112,
+1370145,
+1370176,
+1370209,
+1370240,
+1370273,
+1370304,
+1370337,
+1370368,
+1370401,
+1370432,
+1370465,
+1370496,
+1370529,
+1370560,
+1370593,
+1370624,
+1370657,
+1370688,
+1370721,
+1370752,
+1370785,
+1370816,
+1370849,
+1370880,
+1370913,
+1370944,
+1370977,
+1371008,
+1371041,
+1371072,
+1371105,
+1371136,
+1371169,
+1371200,
+1371233,
+1371264,
+1371297,
+1371328,
+1371361,
+1371392,
+1371425,
+1371456,
+1371489,
+1371520,
+1371553,
+1371584,
+1371617,
+1371651,
+1371681,
+1371936,
+1371969,
+1372000,
+1372033,
+1372064,
+1372129,
+1372160,
+1372193,
+1372224,
+1372257,
+1372288,
+1372321,
+1372352,
+1372385,
+1372419,
+1372468,
+1372512,
+1372545,
+1372576,
+1372609,
+1372669,
+1372672,
+1372705,
+1372736,
+1372769,
+1372829,
+1373184,
+1373217,
+1373248,
+1373281,
+1373312,
+1373345,
+1373376,
+1373409,
+1373440,
+1373473,
+1373504,
+1373565,
+1376003,
+1376065,
+1376100,
+1376325,
+1376356,
+1376453,
+1376484,
+1376613,
+1376644,
+1377382,
+1377445,
+1377510,
+1377557,
+1377693,
+1377802,
+1378005,
+1378067,
+1378101,
+1378141,
+1378308,
+1379985,
+1380125,
+1380358,
+1380420,
+1382022,
+1382533,
+1382589,
+1382865,
+1382920,
+1383261,
+1383429,
+1384004,
+1384209,
+1384292,
+1384349,
+1384456,
+1384772,
+1385669,
+1385937,
+1385988,
+1386725,
+1387078,
+1387165,
+1387505,
+1387524,
+1388477,
+1388549,
+1388646,
+1388676,
+1390181,
+1390214,
+1390277,
+1390406,
+1390469,
+1390502,
+1390641,
+1391069,
+1391075,
+1391112,
+1391453,
+1391569,
+1391645,
+1392644,
+1393957,
+1394150,
+1394213,
+1394278,
+1394341,
+1394429,
+1394692,
+1394789,
+1394820,
+1395077,
+1395110,
+1395165,
+1395208,
+1395549,
+1395601,
+1395716,
+1396227,
+1396260,
+1396469,
+1396548,
+1396582,
+1396637,
+1396740,
+1398277,
+1398308,
+1398341,
+1398436,
+1398501,
+1398564,
+1398725,
+1398788,
+1398821,
+1398852,
+1398909,
+1399652,
+1399715,
+1399761,
+1399812,
+1400166,
+1400197,
+1400262,
+1400337,
+1400388,
+1400419,
+1400486,
+1400517,
+1400573,
+1400868,
+1401085,
+1401124,
+1401341,
+1401380,
+1401597,
+1401860,
+1402109,
+1402116,
+1402365,
+1406980,
+1408102,
+1408165,
+1408198,
+1408261,
+1408294,
+1408369,
+1408390,
+1408421,
+1408477,
+1408520,
+1408861,
+1409028,
+1766557,
+1766916,
+1767677,
+1767780,
+1769373,
+1769499,
+1835036,
+2039812,
+2051549,
+2051588,
+2055005,
+2056193,
+2056445,
+2056801,
+2056989,
+2057124,
+2057157,
+2057188,
+2057522,
+2057540,
+2057981,
+2057988,
+2058173,
+2058180,
+2058237,
+2058244,
+2058333,
+2058340,
+2058429,
+2058436,
+2061908,
+2062429,
+2062948,
+2074573,
+2074606,
+2074653,
+2075140,
+2077213,
+2077252,
+2079005,
+2080260,
+2080659,
+2080693,
+2080733,
+2080773,
+2081297,
+2081517,
+2081550,
+2081585,
+2081629,
+2081797,
+2082045,
+2082321,
+2082348,
+2082411,
+2082477,
+2082510,
+2082541,
+2082574,
+2082605,
+2082638,
+2082669,
+2082702,
+2082733,
+2082766,
+2082797,
+2082830,
+2082861,
+2082894,
+2082925,
+2082958,
+2082993,
+2083053,
+2083086,
+2083121,
+2083243,
+2083345,
+2083453,
+2083473,
+2083596,
+2083629,
+2083662,
+2083693,
+2083726,
+2083757,
+2083790,
+2083825,
+2083922,
+2083948,
+2083986,
+2084093,
+2084113,
+2084147,
+2084177,
+2084253,
+2084356,
+2084541,
+2084548,
+2088893,
+2088954,
+2088989,
+2089009,
+2089107,
+2089137,
+2089229,
+2089262,
+2089297,
+2089330,
+2089361,
+2089388,
+2089425,
+2089480,
+2089809,
+2089874,
+2089969,
+2090016,
+2090861,
+2090897,
+2090926,
+2090964,
+2090987,
+2091028,
+2091041,
+2091885,
+2091922,
+2091950,
+2091986,
+2092013,
+2092046,
+2092081,
+2092109,
+2092142,
+2092177,
+2092228,
+2092547,
+2092580,
+2094019,
+2094084,
+2095101,
+2095172,
+2095389,
+2095428,
+2095645,
+2095684,
+2095901,
+2095940,
+2096061,
+2096147,
+2096210,
+2096244,
+2096277,
+2096307,
+2096381,
+2096405,
+2096434,
+2096565,
+2096637,
+2096954,
+2097045,
+2097117,
+2097156,
+2097565,
+2097572,
+2098429,
+2098436,
+2099069,
+2099076,
+2099165,
+2099172,
+2099677,
+2099716,
+2100189,
+2101252,
+2105213,
+2105361,
+2105469,
+2105578,
+2107037,
+2107125,
+2107401,
+2109098,
+2109237,
+2109770,
+2109821,
+2109973,
+2110365,
+2112021,
+2113445,
+2113501,
+2117636,
+2118589,
+2118660,
+2120253,
+2121732,
+2122749,
+2122762,
+2122909,
+2123268,
+2123817,
+2123844,
+2124105,
+2124157,
+2125828,
+2126813,
+2126833,
+2126852,
+2128029,
+2128132,
+2128401,
+2128425,
+2128605,
+2129920,
+2131201,
+2132484,
+2135005,
+2135048,
+2135389,
+2162692,
+2162909,
+2162948,
+2163005,
+2163012,
+2164445,
+2164452,
+2164541,
+2164612,
+2164669,
+2164708,
+2165469,
+2165489,
+2165514,
+2165789,
+2170884,
+2171594,
+2171805,
+2171889,
+2171908,
+2172765,
+2172913,
+2172957,
+2174980,
+2176797,
+2176964,
+2177053,
+2179076,
+2179109,
+2179229,
+2179237,
+2179325,
+2179461,
+2179588,
+2179741,
+2179748,
+2179869,
+2179876,
+2180765,
+2180869,
+2180989,
+2181093,
+2181130,
+2181405,
+2181649,
+2181949,
+2182148,
+2183082,
+2183153,
+2183197,
+2187268,
+2189021,
+2189105,
+2189316,
+2190045,
+2190090,
+2190340,
+2190973,
+2191114,
+2191389,
+2195460,
+2197821,
+2214922,
+2215933,
+2228230,
+2228261,
+2228294,
+2228324,
+2230021,
+2230513,
+2230749,
+2230858,
+2231496,
+2231837,
+2232325,
+2232390,
+2232420,
+2233862,
+2233957,
+2234086,
+2234149,
+2234225,
+2234298,
+2234321,
+2234461,
+2234884,
+2235709,
+2235912,
+2236253,
+2236421,
+2236516,
+2237669,
+2237830,
+2237861,
+2238141,
+2238152,
+2238481,
+2238621,
+2240517,
+2240582,
+2240612,
+2242150,
+2242245,
+2242534,
+2242596,
+2242737,
+2242877,
+2243080,
+2243421,
+2281476,
+2282853,
+2282886,
+2282917,
+2282950,
+2283013,
+2283206,
+2283237,
+2283293,
+2283528,
+2283869,
+2359300,
+2387453,
+2392073,
+2395261,
+2395665,
+2395805,
+2490372,
+2524669,
+2949124,
+2967357,
+3006468,
+3008701,
+3009028,
+3009062,
+3010557,
+3011045,
+3011171,
+3011613,
+3538948,
+3539037,
+3801109,
+3808989,
+3809301,
+3810557,
+3810613,
+3812518,
+3812581,
+3812693,
+3812774,
+3812986,
+3813221,
+3813493,
+3813541,
+3813781,
+3814725,
+3814869,
+3816413,
+3817493,
+3819589,
+3819701,
+3819741,
+3825685,
+3828477,
+3828746,
+3829341,
+3833856,
+3834689,
+3835520,
+3836353,
+3836605,
+3836609,
+3837184,
+3838017,
+3838848,
+3838909,
+3838912,
+3839005,
+3839040,
+3839101,
+3839136,
+3839229,
+3839264,
+3839421,
+3839424,
+3839681,
+3839837,
+3839841,
+3839901,
+3839905,
+3840157,
+3840161,
+3840512,
+3841345,
+3842176,
+3842269,
+3842272,
+3842429,
+3842464,
+3842749,
+3842752,
+3843005,
+3843009,
+3843840,
+3843933,
+3843936,
+3844093,
+3844096,
+3844285,
+3844288,
+3844349,
+3844416,
+3844669,
+3844673,
+3845504,
+3846337,
+3847168,
+3848001,
+3848832,
+3849665,
+3850496,
+3851329,
+3852160,
+3852993,
+3853824,
+3854657,
+3855581,
+3855616,
+3856434,
+3856449,
+3857266,
+3857281,
+3857472,
+3858290,
+3858305,
+3859122,
+3859137,
+3859328,
+3860146,
+3860161,
+3860978,
+3860993,
+3861184,
+3862002,
+3862017,
+3862834,
+3862849,
+3863040,
+3863858,
+3863873,
+3864690,
+3864705,
+3864896,
+3864929,
+3864989,
+3865032,
+3866653,
+4046852,
+4047005,
+4047012,
+4047901,
+4047908,
+4047997,
+4048004,
+4048061,
+4048100,
+4048157,
+4048164,
+4048509,
+4048516,
+4048669,
+4048676,
+4048733,
+4048740,
+4048797,
+4048964,
+4049021,
+4049124,
+4049181,
+4049188,
+4049245,
+4049252,
+4049309,
+4049316,
+4049437,
+4049444,
+4049533,
+4049540,
+4049597,
+4049636,
+4049693,
+4049700,
+4049757,
+4049764,
+4049821,
+4049828,
+4049885,
+4049892,
+4049949,
+4049956,
+4050045,
+4050052,
+4050109,
+4050148,
+4050301,
+4050308,
+4050557,
+4050564,
+4050717,
+4050724,
+4050877,
+4050884,
+4050941,
+4050948,
+4051293,
+4051300,
+4051869,
+4052004,
+4052125,
+4052132,
+4052317,
+4052324,
+4052893,
+4054546,
+4054621,
+4063253,
+4064669,
+4064789,
+4067997,
+4068373,
+4068861,
+4068917,
+4069373,
+4069429,
+4069917,
+4069941,
+4070429,
+4071434,
+4071805,
+4071957,
+4072957,
+4072981,
+4074909,
+4075029,
+4076413,
+4078805,
+4079741,
+4080149,
+4081533,
+4081685,
+4081981,
+4082197,
+4082269,
+4087829,
+4088893,
+4089365,
+4089565,
+4089589,
+4091837,
+4091925,
+4092573,
+4092949,
+4094141,
+4094165,
+4094333,
+4094997,
+4095549,
+4096021,
+4098045,
+4098069,
+4098109,
+4098133,
+4103965,
+4103989,
+4104125,
+4104213,
+4106205,
+4106261,
+4106397,
+4106773,
+4107549,
+4112245,
+4114493,
+4114613,
+4114973,
+4116501,
+4118749,
+4120597,
+4124317,
+4194308,
+5561085,
+5562372,
+5695165,
+5695492,
+5702621,
+6225924,
+6243293,
+29360186,
+29360221,
+29361178,
+29364253,
+29368325,
+29376029,
+31457308,
+33554397,
+33554460,
+35651549,
+//--Autogenerated -- end of section automatically generated
+};
+
+const int maxUnicode = 0x10ffff;
+const int maskCategory = 0x1F;
+const int nRanges = sizeof(catRanges) / sizeof(catRanges[0]);
+
+}
+
+// Each element in catRanges is the start of a range of Unicode characters in
+// one general category.
+// The value is comprised of a 21-bit character value shifted 5 bits and a 5 bit
+// category matching the CharacterCategory enumeration.
+// Initial version has 3249 entries and adds about 13K to the executable.
+// The array is in ascending order so can be searched using binary search.
+// Therefore the average call takes log2(3249) = 12 comparisons.
+// For speed, it may be an useful to make a linear table for the common values,
+// possibly for 0..0xff for most Western European text or 0..0xfff for most
+// alphabetic languages.
+
+CharacterCategory CategoriseCharacter(int character) {
+	if (character < 0 || character > maxUnicode)
+		return ccCn;
+	const int baseValue = character * (maskCategory+1) + maskCategory;
+	const int *placeAfter = std::lower_bound(catRanges, catRanges+nRanges, baseValue);
+	return static_cast<CharacterCategory>(*(placeAfter-1) & maskCategory);
+}
+
+#ifdef SCI_NAMESPACE
+}
+#endif
diff --git a/scintilla/lexlib/CharacterCategory.h b/scintilla/lexlib/CharacterCategory.h
new file mode 100644
index 0000000..c860050
--- /dev/null
+++ b/scintilla/lexlib/CharacterCategory.h
@@ -0,0 +1,31 @@
+// Scintilla source code edit control
+/** @file CharacterCategory.h
+ ** Returns the Unicode general category of a character.
+ **/
+// Copyright 2013 by Neil Hodgson <neilh@scintilla.org>
+// The License.txt file describes the conditions under which this software may be distributed.
+
+#ifndef CHARACTERCATEGORY_H
+#define CHARACTERCATEGORY_H
+
+#ifdef SCI_NAMESPACE
+namespace Scintilla {
+#endif
+
+enum CharacterCategory {
+	ccLu, ccLl, ccLt, ccLm, ccLo,
+	ccMn, ccMc, ccMe,
+	ccNd, ccNl, ccNo,
+	ccPc, ccPd, ccPs, ccPe, ccPi, ccPf, ccPo,
+	ccSm, ccSc, ccSk, ccSo,
+	ccZs, ccZl, ccZp,
+	ccCc, ccCf, ccCs, ccCo, ccCn
+};
+
+CharacterCategory CategoriseCharacter(int character);
+
+#ifdef SCI_NAMESPACE
+}
+#endif
+
+#endif
diff --git a/scintilla/lexlib/LexAccessor.h b/scintilla/lexlib/LexAccessor.h
index ee238a6..ea772b1 100644
--- a/scintilla/lexlib/LexAccessor.h
+++ b/scintilla/lexlib/LexAccessor.h
@@ -79,6 +79,12 @@ public:
 		}

 		return buf[position - startPos];

 	}

+	IDocumentWithLineEnd *MultiByteAccess() const {

+		if (documentVersion >= dvLineEnd) {

+			return static_cast<IDocumentWithLineEnd *>(pAccess);

+		}

+		return 0;

+	}

 	/** Safe version of operator[], returning a defined value for invalid position. */

 	char SafeGetCharAt(int position, char chDefault=' ') {

 		if (position < startPos || position >= endPos) {

diff --git a/scintilla/lexlib/StyleContext.h b/scintilla/lexlib/StyleContext.h
index 2af34cd..abd69e9 100644
--- a/scintilla/lexlib/StyleContext.h
+++ b/scintilla/lexlib/StyleContext.h
@@ -1,5 +1,5 @@
 // Scintilla source code edit control

-/** @file StyleContext.cxx

+/** @file StyleContext.h

  ** Lexer infrastructure.

  **/

 // Copyright 1998-2004 by Neil Hodgson <neilh@scintilla.org>

@@ -19,67 +19,36 @@ static inline int MakeLowerCase(int ch) {
 		return ch - 'A' + 'a';

 }

 

-inline int UnicodeCodePoint(const unsigned char *us) {

-	if (us[0] < 0xC2) {

-		return us[0];

-	} else if (us[0] < 0xE0) {

-		return ((us[0] & 0x1F) << 6) + (us[1] & 0x3F);

-	} else if (us[0] < 0xF0) {

-		return ((us[0] & 0xF) << 12) + ((us[1] & 0x3F) << 6) + (us[2] & 0x3F);

-	} else if (us[0] < 0xF5) {

-		return ((us[0] & 0x7) << 18) + ((us[1] & 0x3F) << 12) + ((us[2] & 0x3F) << 6) + (us[3] & 0x3F);

-	}

-	return us[0];

-}

-

-inline int BytesInUnicodeCodePoint(int codePoint) {

-	if (codePoint < 0x80)

-		return 1;

-	else if (codePoint < 0x800)

-		return 2;

-	else if (codePoint < 0x10000)

-		return 3;

-	else

-		return 4;

-}

-

 // All languages handled so far can treat all characters >= 0x80 as one class

 // which just continues the current token or starts an identifier if in default.

 // DBCS treated specially as the second character can be < 0x80 and hence

 // syntactically significant. UTF-8 avoids this as all trail bytes are >= 0x80

 class StyleContext {

 	LexAccessor &styler;

+	IDocumentWithLineEnd *multiByteAccess;

 	unsigned int endPos;

 	unsigned int lengthDocument;

+	

+	// Used for optimizing GetRelativeCharacter

+	unsigned int posRelative;

+	unsigned int currentPosLastRelative;

+	int offsetRelative;

+

 	StyleContext &operator=(const StyleContext &);

 

-	void GetNextChar(unsigned int pos) {

-		chNext = static_cast<unsigned char>(styler.SafeGetCharAt(pos+1, 0));

-		if (styler.Encoding() == encUnicode) {

-			if (chNext >= 0x80) {

-				unsigned char bytes[4] = { static_cast<unsigned char>(chNext), 0, 0, 0 };

-				for (int trail=1; trail<3; trail++) {

-					bytes[trail] = static_cast<unsigned char>(styler.SafeGetCharAt(pos+1+trail, 0));

-					if (!((bytes[trail] >= 0x80) && (bytes[trail] < 0xc0))) {

-						bytes[trail] = 0;

-						break;

-					}

-				}

-				chNext = UnicodeCodePoint(bytes);

-			}

-		} else if (styler.Encoding() == encDBCS) {

-			if (styler.IsLeadByte(static_cast<char>(chNext))) {

-				chNext = chNext << 8;

-				chNext |= static_cast<unsigned char>(styler.SafeGetCharAt(pos+2, 0));

-			}

+	void GetNextChar() {

+		if (multiByteAccess) {

+			chNext = multiByteAccess->GetCharacterAndWidth(currentPos+width, &widthNext);

+		} else {

+			chNext = static_cast<unsigned char>(styler.SafeGetCharAt(currentPos+width, 0));

+			widthNext = 1;

 		}

-		// End of line?

-		// Trigger on CR only (Mac style) or either on LF from CR+LF (Dos/Win)

-		// or on LF alone (Unix). Avoid triggering two times on Dos/Win.

+		// End of line determined from line end position, allowing CR, LF, 

+		// CRLF and Unicode line ends as set by document.

 		if (currentLine < lineDocEnd)

-			atLineEnd = static_cast<int>(pos) >= (lineStartNext-1);

+			atLineEnd = static_cast<int>(currentPos) >= (lineStartNext-1);

 		else // Last line

-			atLineEnd = static_cast<int>(pos) >= lineStartNext;

+			atLineEnd = static_cast<int>(currentPos) >= lineStartNext;

 	}

 

 public:

@@ -92,12 +61,18 @@ public:
 	int state;

 	int chPrev;

 	int ch;

+	int width;

 	int chNext;

+	int widthNext;

 

 	StyleContext(unsigned int startPos, unsigned int length,

                         int initStyle, LexAccessor &styler_, char chMask=31) :

 		styler(styler_),

+		multiByteAccess(0),

 		endPos(startPos + length),

+		posRelative(0),

+		currentPosLastRelative(0x7FFFFFFF),

+		offsetRelative(0),

 		currentPos(startPos),

 		currentLine(-1),

 		lineStartNext(-1),

@@ -105,7 +80,12 @@ public:
 		state(initStyle & chMask), // Mask off all bits which aren't in the chMask.

 		chPrev(0),

 		ch(0),

-		chNext(0) {

+		width(0),

+		chNext(0),

+		widthNext(1) {

+		if (styler.Encoding() != enc8bit) {

+			multiByteAccess = styler.MultiByteAccess();

+		}

 		styler.StartAt(startPos, chMask);

 		styler.StartSegment(startPos);

 		currentLine = styler.GetLine(startPos);

@@ -115,21 +95,14 @@ public:
 			endPos++;

 		lineDocEnd = styler.GetLine(lengthDocument);

 		atLineStart = static_cast<unsigned int>(styler.LineStart(currentLine)) == startPos;

-		unsigned int pos = currentPos;

-		ch = static_cast<unsigned char>(styler.SafeGetCharAt(pos, 0));

-		if (styler.Encoding() == encUnicode) {

-			// Get the current char

-			GetNextChar(pos-1);

-			ch = chNext;

-			pos += BytesInUnicodeCodePoint(ch) - 1;

-		} else if (styler.Encoding() == encDBCS) {

-			if (styler.IsLeadByte(static_cast<char>(ch))) {

-				pos++;

-				ch = ch << 8;

-				ch |= static_cast<unsigned char>(styler.SafeGetCharAt(pos, 0));

-			}

-		}

-		GetNextChar(pos);

+

+		// Variable width is now 0 so GetNextChar gets the char at currentPos into chNext/widthNext

+		width = 0;

+		GetNextChar();

+		ch = chNext;

+		width = widthNext;

+

+		GetNextChar();

 	}

 	void Complete() {

 		styler.ColourTo(currentPos - ((currentPos > lengthDocument) ? 2 : 1), state);

@@ -146,23 +119,10 @@ public:
 				lineStartNext = styler.LineStart(currentLine+1);

 			}

 			chPrev = ch;

-			if (styler.Encoding() == encUnicode) {

-				currentPos += BytesInUnicodeCodePoint(ch);

-			} else if (styler.Encoding() == encDBCS) {

-				currentPos++;

-				if (ch >= 0x100)

-					currentPos++;

-			} else {

-				currentPos++;

-			}

+			currentPos += width;

 			ch = chNext;

-			if (styler.Encoding() == encUnicode) {

-				GetNextChar(currentPos + BytesInUnicodeCodePoint(ch)-1);

-			} else if (styler.Encoding() == encDBCS) {

-				GetNextChar(currentPos + ((ch >= 0x100) ? 1 : 0));

-			} else {

-				GetNextChar(currentPos);

-			}

+			width = widthNext;

+			GetNextChar();

 		} else {

 			atLineStart = false;

 			chPrev = ' ';

@@ -176,6 +136,12 @@ public:
 			Forward();

 		}

 	}

+	void ForwardBytes(int nb) {

+		size_t forwardPos = currentPos + nb;

+		while (forwardPos > currentPos) {

+			Forward();

+		}

+	}

 	void ChangeState(int state_) {

 		state = state_;

 	}

@@ -194,6 +160,28 @@ public:
 	int GetRelative(int n) {

 		return static_cast<unsigned char>(styler.SafeGetCharAt(currentPos+n, 0));

 	}

+	int GetRelativeCharacter(int n) {

+		if (n == 0)

+			return ch;

+		if (multiByteAccess) {

+			if ((currentPosLastRelative != currentPos) ||

+				((n > 0) && ((offsetRelative < 0) || (n < offsetRelative))) ||

+				((n < 0) && ((offsetRelative > 0) || (n > offsetRelative)))) {

+				posRelative = currentPos;

+				offsetRelative = 0;

+			}

+			int diffRelative = n - offsetRelative;

+			int posNew = multiByteAccess->GetRelativePosition(posRelative, diffRelative);

+			int ch = multiByteAccess->GetCharacterAndWidth(posNew, 0);

+			posRelative = posNew;

+			currentPosLastRelative = currentPos;

+			offsetRelative = n;

+			return ch;

+		} else {

+			// fast version for single byte encodings

+			return static_cast<unsigned char>(styler.SafeGetCharAt(currentPos + n, 0));

+		}

+	}

 	bool Match(char ch0) const {

 		return ch == static_cast<unsigned char>(ch0);

 	}

diff --git a/scintilla/src/CaseConvert.cxx b/scintilla/src/CaseConvert.cxx
new file mode 100644
index 0000000..647bf72
--- /dev/null
+++ b/scintilla/src/CaseConvert.cxx
@@ -0,0 +1,630 @@
+// Scintilla source code edit control

+// Encoding: UTF-8

+/** @file CaseConvert.cxx

+ ** Case fold characters and convert them to upper or lower case.

+ ** Tables automatically regenerated by scripts/GenerateCharacterCategory.py

+ ** Should only be rarely regenerated for new versions of Unicode.

+ **/

+// Copyright 2013 by Neil Hodgson <neilh@scintilla.org>

+// The License.txt file describes the conditions under which this software may be distributed.

+

+#include <cstring>

+

+#include <vector>

+#include <algorithm>

+

+#include "CaseConvert.h"

+#include "UniConversion.h"

+#include "UnicodeFromUTF8.h"

+

+#ifdef SCI_NAMESPACE

+using namespace Scintilla;

+#endif

+

+namespace {

+	// Use an unnamed namespace to protect the declarations from name conflicts

+

+// Unicode code points are ordered by groups and follow patterns.

+// Most characters (pitch==1) are in ranges for a particular alphabet and their

+// upper case forms are a fixed distance away.

+// Another pattern (pitch==2) is where each lower case letter is preceded by

+// the upper case form. These are also grouped into ranges.

+

+int symmetricCaseConversionRanges[] = {

+//lower, upper, range length, range pitch

+//++Autogenerated -- start of section automatically generated

+//**\(\*\n\)

+97,65,26,1, 

+224,192,23,1, 

+248,216,7,1, 

+257,256,24,2, 

+314,313,8,2, 

+331,330,23,2, 

+462,461,8,2, 

+479,478,9,2, 

+505,504,20,2, 

+547,546,9,2, 

+583,582,5,2, 

+945,913,17,1, 

+963,931,9,1, 

+985,984,12,2, 

+1072,1040,32,1, 

+1104,1024,16,1, 

+1121,1120,17,2, 

+1163,1162,27,2, 

+1218,1217,7,2, 

+1233,1232,44,2, 

+1377,1329,38,1, 

+7681,7680,75,2, 

+7841,7840,48,2, 

+7936,7944,8,1, 

+7952,7960,6,1, 

+7968,7976,8,1, 

+7984,7992,8,1, 

+8000,8008,6,1, 

+8032,8040,8,1, 

+8560,8544,16,1, 

+9424,9398,26,1, 

+11312,11264,47,1, 

+11393,11392,50,2, 

+11520,4256,38,1, 

+42561,42560,23,2, 

+42625,42624,12,2, 

+42787,42786,7,2, 

+42803,42802,31,2, 

+42879,42878,5,2, 

+42913,42912,5,2, 

+65345,65313,26,1, 

+66600,66560,40,1, 

+

+//--Autogenerated -- end of section automatically generated

+};

+

+// Code points that are symmetric but don't fit into a range of similar characters

+// are listed here.

+

+int symmetricCaseConversions[] = {

+//lower, upper

+//++Autogenerated -- start of section automatically generated

+//**1 \(\*\n\)

+255,376, 

+307,306, 

+309,308, 

+311,310, 

+378,377, 

+380,379, 

+382,381, 

+384,579, 

+387,386, 

+389,388, 

+392,391, 

+396,395, 

+402,401, 

+405,502, 

+409,408, 

+410,573, 

+414,544, 

+417,416, 

+419,418, 

+421,420, 

+424,423, 

+429,428, 

+432,431, 

+436,435, 

+438,437, 

+441,440, 

+445,444, 

+447,503, 

+454,452, 

+457,455, 

+460,458, 

+477,398, 

+499,497, 

+501,500, 

+572,571, 

+575,11390, 

+576,11391, 

+578,577, 

+592,11375, 

+593,11373, 

+594,11376, 

+595,385, 

+596,390, 

+598,393, 

+599,394, 

+601,399, 

+603,400, 

+608,403, 

+611,404, 

+613,42893, 

+614,42922, 

+616,407, 

+617,406, 

+619,11362, 

+623,412, 

+625,11374, 

+626,413, 

+629,415, 

+637,11364, 

+640,422, 

+643,425, 

+648,430, 

+649,580, 

+650,433, 

+651,434, 

+652,581, 

+658,439, 

+881,880, 

+883,882, 

+887,886, 

+891,1021, 

+892,1022, 

+893,1023, 

+940,902, 

+941,904, 

+942,905, 

+943,906, 

+972,908, 

+973,910, 

+974,911, 

+983,975, 

+1010,1017, 

+1016,1015, 

+1019,1018, 

+1231,1216, 

+7545,42877, 

+7549,11363, 

+8017,8025, 

+8019,8027, 

+8021,8029, 

+8023,8031, 

+8048,8122, 

+8049,8123, 

+8050,8136, 

+8051,8137, 

+8052,8138, 

+8053,8139, 

+8054,8154, 

+8055,8155, 

+8056,8184, 

+8057,8185, 

+8058,8170, 

+8059,8171, 

+8060,8186, 

+8061,8187, 

+8112,8120, 

+8113,8121, 

+8144,8152, 

+8145,8153, 

+8160,8168, 

+8161,8169, 

+8165,8172, 

+8526,8498, 

+8580,8579, 

+11361,11360, 

+11365,570, 

+11366,574, 

+11368,11367, 

+11370,11369, 

+11372,11371, 

+11379,11378, 

+11382,11381, 

+11500,11499, 

+11502,11501, 

+11507,11506, 

+11559,4295, 

+11565,4301, 

+42874,42873, 

+42876,42875, 

+42892,42891, 

+42897,42896, 

+42899,42898, 

+

+//--Autogenerated -- end of section automatically generated

+};

+

+// Characters that have complex case conversions are listed here.

+// This includes cases where more than one character is needed for a conversion,

+// folding is different to lowering, or (as appropriate) upper(lower(x)) != x or

+// lower(upper(x)) != x.

+

+const char *complexCaseConversions =

+// Original | Folded | Upper | Lower |

+//++Autogenerated -- start of section automatically generated

+//**2 \(\*\n\)

+"µ|μ|Μ||"

+"ß|ss|SS||"

+"İ|i̇||i̇|"

+"ı||I||"

+"ʼn|ʼn|ʼN||"

+"ſ|s|S||"

+"Dž|dž|DŽ|dž|"

+"Lj|lj|LJ|lj|"

+"Nj|nj|NJ|nj|"

+"ǰ|ǰ|J̌||"

+"Dz|dz|DZ|dz|"

+"ͅ|ι|Ι||"

+"ΐ|ΐ|Ϊ́||"

+"ΰ|ΰ|Ϋ́||"

+"ς|σ|Σ||"

+"ϐ|β|Β||"

+"ϑ|θ|Θ||"

+"ϕ|φ|Φ||"

+"ϖ|π|Π||"

+"ϰ|κ|Κ||"

+"ϱ|ρ|Ρ||"

+"ϴ|θ||θ|"

+"ϵ|ε|Ε||"

+"և|եւ|ԵՒ||"

+"ẖ|ẖ|H̱||"

+"ẗ|ẗ|T̈||"

+"ẘ|ẘ|W̊||"

+"ẙ|ẙ|Y̊||"

+"ẚ|aʾ|Aʾ||"

+"ẛ|ṡ|Ṡ||"

+"ẞ|ss||ß|"

+"ὐ|ὐ|Υ̓||"

+"ὒ|ὒ|Υ̓̀||"

+"ὔ|ὔ|Υ̓́||"

+"ὖ|ὖ|Υ̓͂||"

+"ᾀ|ἀι|ἈΙ||"

+"ᾁ|ἁι|ἉΙ||"

+"ᾂ|ἂι|ἊΙ||"

+"ᾃ|ἃι|ἋΙ||"

+"ᾄ|ἄι|ἌΙ||"

+"ᾅ|ἅι|ἍΙ||"

+"ᾆ|ἆι|ἎΙ||"

+"ᾇ|ἇι|ἏΙ||"

+"ᾈ|ἀι|ἈΙ|ᾀ|"

+"ᾉ|ἁι|ἉΙ|ᾁ|"

+"ᾊ|ἂι|ἊΙ|ᾂ|"

+"ᾋ|ἃι|ἋΙ|ᾃ|"

+"ᾌ|ἄι|ἌΙ|ᾄ|"

+"ᾍ|ἅι|ἍΙ|ᾅ|"

+"ᾎ|ἆι|ἎΙ|ᾆ|"

+"ᾏ|ἇι|ἏΙ|ᾇ|"

+"ᾐ|ἠι|ἨΙ||"

+"ᾑ|ἡι|ἩΙ||"

+"ᾒ|ἢι|ἪΙ||"

+"ᾓ|ἣι|ἫΙ||"

+"ᾔ|ἤι|ἬΙ||"

+"ᾕ|ἥι|ἭΙ||"

+"ᾖ|ἦι|ἮΙ||"

+"ᾗ|ἧι|ἯΙ||"

+"ᾘ|ἠι|ἨΙ|ᾐ|"

+"ᾙ|ἡι|ἩΙ|ᾑ|"

+"ᾚ|ἢι|ἪΙ|ᾒ|"

+"ᾛ|ἣι|ἫΙ|ᾓ|"

+"ᾜ|ἤι|ἬΙ|ᾔ|"

+"ᾝ|ἥι|ἭΙ|ᾕ|"

+"ᾞ|ἦι|ἮΙ|ᾖ|"

+"ᾟ|ἧι|ἯΙ|ᾗ|"

+"ᾠ|ὠι|ὨΙ||"

+"ᾡ|ὡι|ὩΙ||"

+"ᾢ|ὢι|ὪΙ||"

+"ᾣ|ὣι|ὫΙ||"

+"ᾤ|ὤι|ὬΙ||"

+"ᾥ|ὥι|ὭΙ||"

+"ᾦ|ὦι|ὮΙ||"

+"ᾧ|ὧι|ὯΙ||"

+"ᾨ|ὠι|ὨΙ|ᾠ|"

+"ᾩ|ὡι|ὩΙ|ᾡ|"

+"ᾪ|ὢι|ὪΙ|ᾢ|"

+"ᾫ|ὣι|ὫΙ|ᾣ|"

+"ᾬ|ὤι|ὬΙ|ᾤ|"

+"ᾭ|ὥι|ὭΙ|ᾥ|"

+"ᾮ|ὦι|ὮΙ|ᾦ|"

+"ᾯ|ὧι|ὯΙ|ᾧ|"

+"ᾲ|ὰι|ᾺΙ||"

+"ᾳ|αι|ΑΙ||"

+"ᾴ|άι|ΆΙ||"

+"ᾶ|ᾶ|Α͂||"

+"ᾷ|ᾶι|Α͂Ι||"

+"ᾼ|αι|ΑΙ|ᾳ|"

+"ι|ι|Ι||"

+"ῂ|ὴι|ῊΙ||"

+"ῃ|ηι|ΗΙ||"

+"ῄ|ήι|ΉΙ||"

+"ῆ|ῆ|Η͂||"

+"ῇ|ῆι|Η͂Ι||"

+"ῌ|ηι|ΗΙ|ῃ|"

+"ῒ|ῒ|Ϊ̀||"

+"ΐ|ΐ|Ϊ́||"

+"ῖ|ῖ|Ι͂||"

+"ῗ|ῗ|Ϊ͂||"

+"ῢ|ῢ|Ϋ̀||"

+"ΰ|ΰ|Ϋ́||"

+"ῤ|ῤ|Ρ̓||"

+"ῦ|ῦ|Υ͂||"

+"ῧ|ῧ|Ϋ͂||"

+"ῲ|ὼι|ῺΙ||"

+"ῳ|ωι|ΩΙ||"

+"ῴ|ώι|ΏΙ||"

+"ῶ|ῶ|Ω͂||"

+"ῷ|ῶι|Ω͂Ι||"

+"ῼ|ωι|ΩΙ|ῳ|"

+"Ω|ω||ω|"

+"K|k||k|"

+"Å|å||å|"

+"ff|ff|FF||"

+"fi|fi|FI||"

+"fl|fl|FL||"

+"ffi|ffi|FFI||"

+"ffl|ffl|FFL||"

+"ſt|st|ST||"

+"st|st|ST||"

+"ﬓ|մն|ՄՆ||"

+"ﬔ|մե|ՄԵ||"

+"ﬕ|մի|ՄԻ||"

+"ﬖ|վն|ՎՆ||"

+"ﬗ|մխ|ՄԽ||"

+

+//--Autogenerated -- end of section automatically generated

+;

+

+class CaseConverter : public ICaseConverter {

+	// Maximum length of a case conversion result is 6 bytes in UTF-8

+	enum { maxConversionLength=6 };

+	struct ConversionString {

+		char conversion[maxConversionLength+1];

+	};

+	// Conversions are initially store in a vector of structs but then decomposed into

+	// parallel arrays as that is about 10% faster to search.

+	struct CharacterConversion {

+		int character;

+		ConversionString conversion;

+		CharacterConversion(int character_=0, const char *conversion_="") : character(character_) {

+			strcpy(conversion.conversion, conversion_);

+		}

+		bool operator<(const CharacterConversion &other) const {

+			return character < other.character;

+		}

+	};

+	typedef std::vector<CharacterConversion> CharacterToConversion;

+	CharacterToConversion characterToConversion;

+	// The parallel arrays 

+	std::vector<int> characters;

+	std::vector<ConversionString> conversions;

+

+public:

+	CaseConverter() {

+	}

+	bool Initialised() const {

+		return characters.size() > 0;

+	}

+	void Add(int character, const char *conversion) {

+		characterToConversion.push_back(CharacterConversion(character, conversion));

+	}

+	const char *Find(int character) {

+		const std::vector<int>::iterator it = std::lower_bound(characters.begin(), characters.end(), character);

+		if (it == characters.end())

+			return 0;

+		else if (*it == character)

+			return conversions[it - characters.begin()].conversion;

+		else

+			return 0;

+	}

+	size_t CaseConvertString(char *converted, size_t sizeConverted, const char *mixed, size_t lenMixed) {

+		size_t lenConverted = 0;

+		size_t mixedPos = 0;

+		unsigned char bytes[UTF8MaxBytes + 1];

+		while (mixedPos < lenMixed) {

+			const unsigned char leadByte = static_cast<unsigned char>(mixed[mixedPos]);

+			const char *caseConverted = 0;

+			size_t lenMixedChar = 1;

+			if (UTF8IsAscii(leadByte)) {

+				caseConverted = Find(leadByte);

+			} else {

+				bytes[0] = leadByte;

+				const int widthCharBytes = UTF8BytesOfLead[leadByte];

+				for (int b=1; b<widthCharBytes; b++) {

+					bytes[b] = (mixedPos+b < lenMixed) ? mixed[mixedPos+b] : 0;

+				}

+				int classified = UTF8Classify(bytes, widthCharBytes);

+				if (!(classified & UTF8MaskInvalid)) {

+					// valid UTF-8

+					lenMixedChar = classified & UTF8MaskWidth;

+					int character = UnicodeFromUTF8(bytes);

+					caseConverted = Find(character);

+				}

+			}

+			if (caseConverted) {

+				// Character has a conversion so copy that conversion in

+				while (*caseConverted) {

+					converted[lenConverted++] = *caseConverted++;

+					if (lenConverted >= sizeConverted)

+						return 0;

+				}

+			} else {

+				// Character has no conversion so copy the input to output

+				for (size_t i=0; i<lenMixedChar; i++) {

+					converted[lenConverted++] = mixed[mixedPos+i];

+					if (lenConverted >= sizeConverted)

+						return 0;

+				}

+			}

+			mixedPos += lenMixedChar;

+		}

+		return lenConverted;

+	}

+	void FinishedAdding() {

+		std::sort(characterToConversion.begin(), characterToConversion.end());

+		characters.reserve(characterToConversion.size());

+		conversions.reserve(characterToConversion.size());

+		for (CharacterToConversion::iterator it = characterToConversion.begin(); it != characterToConversion.end(); ++it) {

+			characters.push_back(it->character);

+			conversions.push_back(it->conversion);

+		}

+		// Empty the original calculated data completely

+		CharacterToConversion().swap(characterToConversion);

+	}

+};

+

+CaseConverter caseConvFold;

+CaseConverter caseConvUp;

+CaseConverter caseConvLow;

+

+void UTF8FromUTF32Character(int uch, char *putf) {

+	size_t k = 0;

+	if (uch < 0x80) {

+		putf[k++] = static_cast<char>(uch);

+	} else if (uch < 0x800) {

+		putf[k++] = static_cast<char>(0xC0 | (uch >> 6));

+		putf[k++] = static_cast<char>(0x80 | (uch & 0x3f));

+	} else if (uch < 0x10000) {

+		putf[k++] = static_cast<char>(0xE0 | (uch >> 12));

+		putf[k++] = static_cast<char>(0x80 | ((uch >> 6) & 0x3f));

+		putf[k++] = static_cast<char>(0x80 | (uch & 0x3f));

+	} else {

+		putf[k++] = static_cast<char>(0xF0 | (uch >> 18));

+		putf[k++] = static_cast<char>(0x80 | ((uch >> 12) & 0x3f));

+		putf[k++] = static_cast<char>(0x80 | ((uch >> 6) & 0x3f));

+		putf[k++] = static_cast<char>(0x80 | (uch & 0x3f));

+	}

+	putf[k] = 0;

+}

+

+void AddSymmetric(enum CaseConversion conversion, int lower,int upper) {

+	char lowerUTF8[UTF8MaxBytes+1];

+	UTF8FromUTF32Character(lower, lowerUTF8);

+	char upperUTF8[UTF8MaxBytes+1];

+	UTF8FromUTF32Character(upper, upperUTF8);

+

+	switch (conversion) {

+	case CaseConversionFold:

+		caseConvFold.Add(upper, lowerUTF8);

+		break;

+	case CaseConversionUpper:

+		caseConvUp.Add(lower, upperUTF8);

+		break;

+	case CaseConversionLower:

+		caseConvLow.Add(upper, lowerUTF8);

+		break;

+	}

+}

+

+void SetupConversions(enum CaseConversion conversion) {

+	// First initialize for the symmetric ranges

+	for (size_t i=0; i<sizeof(symmetricCaseConversionRanges)/sizeof(symmetricCaseConversionRanges[0]);) {

+		int lower = symmetricCaseConversionRanges[i++];

+		int upper = symmetricCaseConversionRanges[i++];

+		int length = symmetricCaseConversionRanges[i++];

+		int pitch = symmetricCaseConversionRanges[i++];

+		for (int j=0;j<length*pitch;j+=pitch) {

+			AddSymmetric(conversion, lower+j, upper+j);

+		}

+	}

+	// Add the symmetric singletons

+	for (size_t i=0; i<sizeof(symmetricCaseConversions)/sizeof(symmetricCaseConversions[0]);) {

+		int lower = symmetricCaseConversions[i++];

+		int upper = symmetricCaseConversions[i++];

+		AddSymmetric(conversion, lower, upper);

+	}

+	// Add the complex cases

+	const char *sComplex = complexCaseConversions;

+	while (*sComplex) {

+		// Longest ligature is 3 character so 5 for safety

+		const size_t lenUTF8 = 5*UTF8MaxBytes+1;

+		char originUTF8[lenUTF8];

+		char foldedUTF8[lenUTF8];

+		char lowerUTF8[lenUTF8];

+		char upperUTF8[lenUTF8];

+		size_t i = 0;

+		while (*sComplex && *sComplex != '|') {

+			originUTF8[i++] = *sComplex;

+			sComplex++;

+		}

+		sComplex++;

+		originUTF8[i] = 0;

+		i = 0;

+		while (*sComplex && *sComplex != '|') {

+			foldedUTF8[i++] = *sComplex;

+			sComplex++;

+		}

+		sComplex++;

+		foldedUTF8[i] = 0;

+		i = 0;

+		while (*sComplex && *sComplex != '|') {

+			upperUTF8[i++] = *sComplex;

+			sComplex++;

+		}

+		sComplex++;

+		upperUTF8[i] = 0;

+		i = 0;

+		while (*sComplex && *sComplex != '|') {

+			lowerUTF8[i++] = *sComplex;

+			sComplex++;

+		}

+		sComplex++;

+		lowerUTF8[i] = 0;

+

+		int character = UnicodeFromUTF8(reinterpret_cast<unsigned char *>(originUTF8));

+

+		if (conversion == CaseConversionFold && foldedUTF8[0]) {

+			caseConvFold.Add(character, foldedUTF8);

+		}

+

+		if (conversion == CaseConversionUpper && upperUTF8[0]) {

+			caseConvUp.Add(character, upperUTF8);

+		}

+

+		if (conversion == CaseConversionLower && lowerUTF8[0]) {

+			caseConvLow.Add(character, lowerUTF8);

+		}

+	}

+

+	switch (conversion) {

+	case CaseConversionFold:

+		caseConvFold.FinishedAdding();

+		break;

+	case CaseConversionUpper:

+		caseConvUp.FinishedAdding();

+		break;

+	case CaseConversionLower:

+		caseConvLow.FinishedAdding();

+		break;

+	}

+}

+

+CaseConverter *ConverterForConversion(enum CaseConversion conversion) {

+	switch (conversion) {

+	case CaseConversionFold:

+		return &caseConvFold;

+	case CaseConversionUpper:

+		return &caseConvUp;

+	case CaseConversionLower:

+		return &caseConvLow;

+	}

+	return 0;

+}

+

+}

+

+#ifdef SCI_NAMESPACE

+namespace Scintilla {

+#endif

+

+ICaseConverter *ConverterFor(enum CaseConversion conversion) {

+	CaseConverter *pCaseConv = ConverterForConversion(conversion);

+	if (!pCaseConv->Initialised())

+		SetupConversions(conversion);

+	return pCaseConv;

+}

+

+const char *CaseConvert(int character, enum CaseConversion conversion) {

+	CaseConverter *pCaseConv = ConverterForConversion(conversion);

+	if (!pCaseConv->Initialised())

+		SetupConversions(conversion);

+	return pCaseConv->Find(character);

+}

+

+size_t CaseConvertString(char *converted, size_t sizeConverted, const char *mixed, size_t lenMixed, enum CaseConversion conversion) {

+	CaseConverter *pCaseConv = ConverterForConversion(conversion);

+	if (!pCaseConv->Initialised())

+		SetupConversions(conversion);

+	return pCaseConv->CaseConvertString(converted, sizeConverted, mixed, lenMixed);

+}

+

+#ifdef SCI_NAMESPACE

+}

+#endif

diff --git a/scintilla/src/CaseConvert.h b/scintilla/src/CaseConvert.h
new file mode 100644
index 0000000..60de227
--- /dev/null
+++ b/scintilla/src/CaseConvert.h
@@ -0,0 +1,47 @@
+// Scintilla source code edit control
+// Encoding: UTF-8
+/** @file CaseConvert.h
+ ** Performs Unicode case conversions.
+ ** Does not handle locale-sensitive case conversion.
+ **/
+// Copyright 2013 by Neil Hodgson <neilh@scintilla.org>
+// The License.txt file describes the conditions under which this software may be distributed.
+
+#ifndef CASECONVERT_H
+#define CASECONVERT_H
+
+#ifdef SCI_NAMESPACE
+namespace Scintilla {
+#endif
+
+enum CaseConversion {
+	CaseConversionFold,
+	CaseConversionUpper,
+	CaseConversionLower
+};
+
+class ICaseConverter {
+public:
+	virtual size_t CaseConvertString(char *converted, size_t sizeConverted, const char *mixed, size_t lenMixed) = 0;
+};
+
+ICaseConverter *ConverterFor(enum CaseConversion conversion);
+
+// Returns a UTF-8 string. Empty when no conversion
+const char *CaseConvert(int character, enum CaseConversion conversion);
+
+// When performing CaseConvertString, the converted value may be up to 3 times longer than the input.
+// Ligatures are often decomposed into multiple characters and long cases include:
+// ΐ "\xce\x90" folds to ΐ "\xce\xb9\xcc\x88\xcc\x81"
+const int maxExpansionCaseConversion=3;
+
+// Converts a mixed case string using a particular conversion.
+// Result may be a different length to input and the length is the return value.
+// If there is not enough space then 0 is returned.
+size_t CaseConvertString(char *converted, size_t sizeConverted, const char *mixed, size_t lenMixed, enum CaseConversion conversion);
+
+#ifdef SCI_NAMESPACE
+}
+#endif
+
+#endif
diff --git a/scintilla/src/CaseFolder.cxx b/scintilla/src/CaseFolder.cxx
new file mode 100644
index 0000000..44a94da
--- /dev/null
+++ b/scintilla/src/CaseFolder.cxx
@@ -0,0 +1,68 @@
+// Scintilla source code edit control
+/** @file CaseFolder.cxx
+ ** Classes for case folding.
+ **/
+// Copyright 1998-2013 by Neil Hodgson <neilh@scintilla.org>
+// The License.txt file describes the conditions under which this software may be distributed.
+
+#include <vector>
+#include <algorithm>
+
+#include "CaseConvert.h"
+#include "UniConversion.h"
+#include "CaseFolder.h"
+
+#ifdef SCI_NAMESPACE
+using namespace Scintilla;
+#endif
+
+CaseFolder::~CaseFolder() {
+}
+
+CaseFolderTable::CaseFolderTable() {
+	for (size_t iChar=0; iChar<sizeof(mapping); iChar++) {
+		mapping[iChar] = static_cast<char>(iChar);
+	}
+}
+
+CaseFolderTable::~CaseFolderTable() {
+}
+
+size_t CaseFolderTable::Fold(char *folded, size_t sizeFolded, const char *mixed, size_t lenMixed) {
+	if (lenMixed > sizeFolded) {
+		return 0;
+	} else {
+		for (size_t i=0; i<lenMixed; i++) {
+			folded[i] = mapping[static_cast<unsigned char>(mixed[i])];
+		}
+		return lenMixed;
+	}
+}
+
+void CaseFolderTable::SetTranslation(char ch, char chTranslation) {
+	mapping[static_cast<unsigned char>(ch)] = chTranslation;
+}
+
+void CaseFolderTable::StandardASCII() {
+	for (size_t iChar=0; iChar<sizeof(mapping); iChar++) {
+		if (iChar >= 'A' && iChar <= 'Z') {
+			mapping[iChar] = static_cast<char>(iChar - 'A' + 'a');
+		} else {
+			mapping[iChar] = static_cast<char>(iChar);
+		}
+	}
+}
+
+CaseFolderUnicode::CaseFolderUnicode() {
+	StandardASCII();
+	converter = ConverterFor(CaseConversionFold);
+}
+
+size_t CaseFolderUnicode::Fold(char *folded, size_t sizeFolded, const char *mixed, size_t lenMixed) {
+	if ((lenMixed == 1) && (sizeFolded > 0)) {
+		folded[0] = mapping[static_cast<unsigned char>(mixed[0])];
+		return 1;
+	} else {
+		return converter->CaseConvertString(folded, sizeFolded, mixed, lenMixed);
+	}
+}
diff --git a/scintilla/src/CaseFolder.h b/scintilla/src/CaseFolder.h
new file mode 100644
index 0000000..2d754d4
--- /dev/null
+++ b/scintilla/src/CaseFolder.h
@@ -0,0 +1,45 @@
+// Scintilla source code edit control
+/** @file CaseFolder.h
+ ** Classes for case folding.
+ **/
+// Copyright 1998-2013 by Neil Hodgson <neilh@scintilla.org>
+// The License.txt file describes the conditions under which this software may be distributed.
+
+#ifndef CASEFOLDER_H
+#define CASEFOLDER_H
+
+#ifdef SCI_NAMESPACE
+namespace Scintilla {
+#endif
+
+class CaseFolder {
+public:
+	virtual ~CaseFolder();
+	virtual size_t Fold(char *folded, size_t sizeFolded, const char *mixed, size_t lenMixed) = 0;
+};
+
+class CaseFolderTable : public CaseFolder {
+protected:
+	char mapping[256];
+public:
+	CaseFolderTable();
+	virtual ~CaseFolderTable();
+	virtual size_t Fold(char *folded, size_t sizeFolded, const char *mixed, size_t lenMixed);
+	void SetTranslation(char ch, char chTranslation);
+	void StandardASCII();
+};
+
+class ICaseConverter;
+
+class CaseFolderUnicode : public CaseFolderTable {
+	ICaseConverter *converter;
+public:
+	CaseFolderUnicode();
+	virtual size_t Fold(char *folded, size_t sizeFolded, const char *mixed, size_t lenMixed);
+};
+
+#ifdef SCI_NAMESPACE
+}
+#endif
+
+#endif
diff --git a/scintilla/src/Catalogue.cxx b/scintilla/src/Catalogue.cxx
index 448e93a..fc06738 100644
--- a/scintilla/src/Catalogue.cxx
+++ b/scintilla/src/Catalogue.cxx
@@ -85,9 +85,9 @@ int Scintilla_LinkLexers() {
 	//LINK_LEXER(lmAbaqus);

 	//LINK_LEXER(lmAda);

 	LINK_LEXER(lmAHK);

-	//LINK_LEXER(lmAns1);

 	//LINK_LEXER(lmAPDL);

 	LINK_LEXER(lmAsm);

+	//LINK_LEXER(lmAsn1);

 	//LINK_LEXER(lmASY);

 	LINK_LEXER(lmAU3);

 	//LINK_LEXER(lmAVE);

diff --git a/scintilla/src/CellBuffer.cxx b/scintilla/src/CellBuffer.cxx
index 3c955dc..7d322a9 100644
--- a/scintilla/src/CellBuffer.cxx
+++ b/scintilla/src/CellBuffer.cxx
@@ -168,7 +168,7 @@ void UndoHistory::EnsureUndoRoom() {
 	}

 }

 

-void UndoHistory::AppendAction(actionType at, int position, const char *data, int lengthData,

+const char *UndoHistory::AppendAction(actionType at, int position, const char *data, int lengthData,

 	bool &startSequence, bool mayCoalesce) {

 	EnsureUndoRoom();

 	//Platform::DebugPrintf("%% %d action %d %d %d\n", at, position, lengthData, currentAction);

@@ -232,10 +232,12 @@ void UndoHistory::AppendAction(actionType at, int position, const char *data, in
 		currentAction++;

 	}

 	startSequence = oldCurrentAction != currentAction;

+	int actionWithData = currentAction;

 	actions[currentAction].Create(at, position, data, lengthData, mayCoalesce);

 	currentAction++;

 	actions[currentAction].Create(startAction);

 	maxAction = currentAction;

+	return actions[actionWithData].data;

 }

 

 void UndoHistory::BeginUndoAction() {

@@ -393,13 +395,13 @@ int CellBuffer::GapPosition() const {
 

 // The char* returned is to an allocation owned by the undo history

 const char *CellBuffer::InsertString(int position, const char *s, int insertLength, bool &startSequence) {

-	char *data = 0;

 	// InsertString and DeleteChars are the bottleneck though which all changes occur

+	const char *data = s;

 	if (!readOnly) {

 		if (collectingUndo) {

 			// Save into the undo/redo stack, but only the characters - not the formatting

 			// This takes up about half load time

-			uh.AppendAction(insertAction, position, s, insertLength, startSequence);

+			data = uh.AppendAction(insertAction, position, s, insertLength, startSequence);

 		}

 

 		BasicInsertString(position, s, insertLength);

@@ -437,13 +439,13 @@ bool CellBuffer::SetStyleFor(int position, int lengthStyle, char styleValue, cha
 const char *CellBuffer::DeleteChars(int position, int deleteLength, bool &startSequence) {

 	// InsertString and DeleteChars are the bottleneck though which all changes occur

 	PLATFORM_ASSERT(deleteLength > 0);

-	char *data = 0;

+	const char *data = 0;

 	if (!readOnly) {

 		if (collectingUndo) {

 			// Save into the undo/redo stack, but only the characters - not the formatting

 			// The gap would be moved to position anyway for the deletion so this doesn't cost extra

-			const char *data = substance.RangePointer(position, deleteLength);

-			uh.AppendAction(removeAction, position, data, deleteLength, startSequence);

+			data = substance.RangePointer(position, deleteLength);

+			data = uh.AppendAction(removeAction, position, data, deleteLength, startSequence);

 		}

 

 		BasicDeleteChars(position, deleteLength);

diff --git a/scintilla/src/CellBuffer.h b/scintilla/src/CellBuffer.h
index 7acdfd0..15d2174 100644
--- a/scintilla/src/CellBuffer.h
+++ b/scintilla/src/CellBuffer.h
@@ -105,7 +105,7 @@ public:
 	UndoHistory();

 	~UndoHistory();

 

-	void AppendAction(actionType at, int position, const char *data, int length, bool &startSequence, bool mayCoalesce=true);

+	const char *AppendAction(actionType at, int position, const char *data, int length, bool &startSequence, bool mayCoalesce=true);

 

 	void BeginUndoAction();

 	void EndUndoAction();

diff --git a/scintilla/src/Document.cxx b/scintilla/src/Document.cxx
index 66cef39..64f6b46 100644
--- a/scintilla/src/Document.cxx
+++ b/scintilla/src/Document.cxx
@@ -28,6 +28,7 @@
 #include "CharClassify.h"

 #include "CharacterSet.h"

 #include "Decoration.h"

+#include "CaseFolder.h"

 #include "Document.h"

 #include "RESearch.h"

 #include "UniConversion.h"

@@ -699,6 +700,79 @@ bool Document::NextCharacter(int &pos, int moveDir) const {
 	}

 }

 

+static inline int UnicodeFromBytes(const unsigned char *us) {

+	if (us[0] < 0xC2) {

+		return us[0];

+	} else if (us[0] < 0xE0) {

+		return ((us[0] & 0x1F) << 6) + (us[1] & 0x3F);

+	} else if (us[0] < 0xF0) {

+		return ((us[0] & 0xF) << 12) + ((us[1] & 0x3F) << 6) + (us[2] & 0x3F);

+	} else if (us[0] < 0xF5) {

+		return ((us[0] & 0x7) << 18) + ((us[1] & 0x3F) << 12) + ((us[2] & 0x3F) << 6) + (us[3] & 0x3F);

+	}

+	return us[0];

+}

+

+// Return -1  on out-of-bounds

+int SCI_METHOD Document::GetRelativePosition(int positionStart, int characterOffset) const {

+	int pos = positionStart;

+	if (dbcsCodePage) {

+		const int increment = (characterOffset > 0) ? 1 : -1;

+		while (characterOffset != 0) {

+			const int posNext = NextPosition(pos, increment);

+			if (posNext == pos)

+				return INVALID_POSITION;

+			pos = posNext;

+			characterOffset -= increment;

+		}

+	} else {

+		pos = positionStart + characterOffset;

+		if ((pos < 0) || (pos > Length()))

+			return INVALID_POSITION;

+	}

+	return pos;

+}

+

+int SCI_METHOD Document::GetCharacterAndWidth(int position, int *pWidth) const {

+	int character;

+	int bytesInCharacter = 1;

+	if (dbcsCodePage) {

+		const unsigned char leadByte = static_cast<unsigned char>(cb.CharAt(position));

+		if (SC_CP_UTF8 == dbcsCodePage) {

+			if (UTF8IsAscii(leadByte)) {

+				// Single byte character or invalid

+				character =  leadByte;

+			} else {

+				const int widthCharBytes = UTF8BytesOfLead[leadByte];

+				unsigned char charBytes[UTF8MaxBytes] = {leadByte,0,0,0};

+				for (int b=1; b<widthCharBytes; b++)

+					charBytes[b] = static_cast<unsigned char>(cb.CharAt(position+b));

+				int utf8status = UTF8Classify(charBytes, widthCharBytes);

+				if (utf8status & UTF8MaskInvalid) {

+					// Report as singleton surrogate values which are invalid Unicode

+					character =  0xDC80 + leadByte;

+				} else {

+					bytesInCharacter = utf8status & UTF8MaskWidth;

+					character = UnicodeFromBytes(charBytes);

+				}

+			}

+		} else {

+			if (IsDBCSLeadByte(leadByte)) {

+				bytesInCharacter = 2;

+				character = (leadByte << 8) | static_cast<unsigned char>(cb.CharAt(position+1));

+			} else {

+				character = leadByte;

+			}

+		}

+	} else {

+		character = cb.CharAt(position);

+	}

+	if (pWidth) {

+		*pWidth = bytesInCharacter;

+	}

+	return character;

+}

+

 int SCI_METHOD Document::CodePage() const {

 	return dbcsCodePage;

 }

@@ -1423,47 +1497,6 @@ bool Document::IsWordAt(int start, int end) const {
 	return IsWordStartAt(start) && IsWordEndAt(end);

 }

 

-static inline char MakeLowerCase(char ch) {

-	if (ch < 'A' || ch > 'Z')

-		return ch;

-	else

-		return static_cast<char>(ch - 'A' + 'a');

-}

-

-CaseFolderTable::CaseFolderTable() {

-	for (size_t iChar=0; iChar<sizeof(mapping); iChar++) {

-		mapping[iChar] = static_cast<char>(iChar);

-	}

-}

-

-CaseFolderTable::~CaseFolderTable() {

-}

-

-size_t CaseFolderTable::Fold(char *folded, size_t sizeFolded, const char *mixed, size_t lenMixed) {

-	if (lenMixed > sizeFolded) {

-		return 0;

-	} else {

-		for (size_t i=0; i<lenMixed; i++) {

-			folded[i] = mapping[static_cast<unsigned char>(mixed[i])];

-		}

-		return lenMixed;

-	}

-}

-

-void CaseFolderTable::SetTranslation(char ch, char chTranslation) {

-	mapping[static_cast<unsigned char>(ch)] = chTranslation;

-}

-

-void CaseFolderTable::StandardASCII() {

-	for (size_t iChar=0; iChar<sizeof(mapping); iChar++) {

-		if (iChar >= 'A' && iChar <= 'Z') {

-			mapping[iChar] = static_cast<char>(iChar - 'A' + 'a');

-		} else {

-			mapping[iChar] = static_cast<char>(iChar);

-		}

-	}

-}

-

 bool Document::MatchesWordOptions(bool word, bool wordStart, int pos, int length) const {

 	return (!word && !wordStart) ||

 			(word && IsWordAt(pos, pos + length)) ||

diff --git a/scintilla/src/Document.h b/scintilla/src/Document.h
index cd7eb12..94e288e 100644
--- a/scintilla/src/Document.h
+++ b/scintilla/src/Document.h
@@ -155,24 +155,6 @@ public:
 	bool isEnabled;

 };

 

-class CaseFolder {

-public:

-	virtual ~CaseFolder() {

-	}

-	virtual size_t Fold(char *folded, size_t sizeFolded, const char *mixed, size_t lenMixed) = 0;

-};

-

-class CaseFolderTable : public CaseFolder {

-protected:

-	char mapping[256];

-public:

-	CaseFolderTable();

-	virtual ~CaseFolderTable();

-	virtual size_t Fold(char *folded, size_t sizeFolded, const char *mixed, size_t lenMixed);

-	void SetTranslation(char ch, char chTranslation);

-	void StandardASCII();

-};

-

 class Document;

 

 class LexInterface {

@@ -279,6 +261,8 @@ public:
 	int MovePositionOutsideChar(int pos, int moveDir, bool checkLineEnd=true);

 	int NextPosition(int pos, int moveDir) const;

 	bool NextCharacter(int &pos, int moveDir) const;	// Returns true if pos changed

+	int SCI_METHOD GetRelativePosition(int positionStart, int characterOffset) const;

+	int SCI_METHOD GetCharacterAndWidth(int position, int *pWidth) const;

 	int SCI_METHOD CodePage() const;

 	bool SCI_METHOD IsDBCSLeadByte(char ch) const;

 	int SafeSegment(const char *text, int length, int lengthSegment) const;

diff --git a/scintilla/src/Editor.cxx b/scintilla/src/Editor.cxx
index 33ea542..6bf8c5d 100644
--- a/scintilla/src/Editor.cxx
+++ b/scintilla/src/Editor.cxx
@@ -36,6 +36,7 @@
 #include "ViewStyle.h"

 #include "CharClassify.h"

 #include "Decoration.h"

+#include "CaseFolder.h"

 #include "Document.h"

 #include "UniConversion.h"

 #include "Selection.h"

@@ -116,6 +117,7 @@ Editor::Editor() {
 	hasFocus = false;

 	hideSelection = false;

 	inOverstrike = false;

+	drawOverstrikeCaret = true;

 	errorStatus = 0;

 	mouseDownCaptures = true;

 

@@ -212,8 +214,6 @@ Editor::Editor() {
 

 	wrapState = eWrapNone;

 	wrapWidth = LineLayout::wrapWidthInfinite;

-	wrapStart = wrapLineLarge;

-	wrapEnd = wrapLineLarge;

 	wrapVisualFlags = 0;

 	wrapVisualFlagsLocation = 0;

 	wrapVisualStartIndent = 0;

@@ -961,8 +961,8 @@ int Editor::MovePositionTo(SelectionPosition newPos, Selection::selTypes selt, b
 	int currentLine = pdoc->LineFromPosition(newPos.Position());

 	if (ensureVisible) {

 		// In case in need of wrapping to ensure DisplayFromDoc works.

-		if (currentLine >= wrapStart)

-			WrapLines(true, -1);

+		if (currentLine >= wrapPending.start)

+			WrapLines(wsAll);

 		XYScrollPosition newXY = XYScrollToMakeVisible(

 			SelectionRange(posDrag.IsValid() ? posDrag : sel.RangeMain().caret), xysDefault);

 		if (simpleCaret && (newXY.xOffset == xOffset)) {

@@ -1541,17 +1541,12 @@ void Editor::UpdateSystemCaret() {
 }

 

 void Editor::NeedWrapping(int docLineStart, int docLineEnd) {

-	docLineStart = Platform::Clamp(docLineStart, 0, pdoc->LinesTotal());

-	if (wrapStart > docLineStart) {

-		wrapStart = docLineStart;

+//Platform::DebugPrintf("\nNeedWrapping: %0d..%0d\n", docLineStart, docLineEnd);

+	if (wrapPending.AddRange(docLineStart, docLineEnd)) {

 		llc.Invalidate(LineLayout::llPositions);

 	}

-	if (wrapEnd < docLineEnd) {

-		wrapEnd = docLineEnd;

-	}

-	wrapEnd = Platform::Clamp(wrapEnd, 0, pdoc->LinesTotal());

 	// Wrap lines during idle.

-	if ((wrapState != eWrapNone) && (wrapEnd != wrapStart)) {

+	if ((wrapState != eWrapNone) && wrapPending.NeedsWrap()) {

 		SetIdle(true);

 	}

 }

@@ -1567,117 +1562,97 @@ bool Editor::WrapOneLine(Surface *surface, int lineToWrap) {
 		(vs.annotationVisible ? pdoc->AnnotationLines(lineToWrap) : 0));

 }

 

-// Check if wrapping needed and perform any needed wrapping.

-// fullwrap: if true, all lines which need wrapping will be done,

-//           in this single call.

-// priorityWrapLineStart: If greater than or equal to zero, all lines starting from

-//           here to 1 page + 100 lines past will be wrapped (even if there are

-//           more lines under wrapping process in idle).

-// If it is neither fullwrap, nor priorityWrap, then 1 page + 100 lines will be

-// wrapped, if there are any wrapping going on in idle. (Generally this

-// condition is called only from idler).

+// Perform  wrapping for a subset of the lines needing wrapping.

+// wsAll: wrap all lines which need wrapping in this single call

+// wsVisible: wrap currently visible lines

+// wsIdle: wrap one page + 100 lines

 // Return true if wrapping occurred.

-bool Editor::WrapLines(bool fullWrap, int priorityWrapLineStart) {

-	// If there are any pending wraps, do them during idle if possible.

-	int linesInOneCall = LinesOnScreen() + 100;

-	if (priorityWrapLineStart >= 0) {

-		// Using DocFromDisplay() here may result in chicken and egg problem in certain corner cases,

-		// which will hopefully be handled by added 100 lines. If some lines are still missed, idle wrapping will catch on.

-		int docLinesInOneCall = cs.DocFromDisplay(topLine + LinesOnScreen() + 100) - cs.DocFromDisplay(topLine);

-		linesInOneCall = Platform::Maximum(linesInOneCall, docLinesInOneCall);

-	}

-	if (wrapState != eWrapNone) {

-		if (wrapStart < wrapEnd) {

-			if (!SetIdle(true)) {

-				// Idle processing not supported so full wrap required.

-				fullWrap = true;

-			}

-		}

-		if (!fullWrap && priorityWrapLineStart >= 0 &&

-		        // .. and if the paint window is outside pending wraps

-		        (((priorityWrapLineStart + linesInOneCall) < wrapStart) ||

-		         (priorityWrapLineStart > wrapEnd))) {

-			// No priority wrap pending

-			return false;

-		}

-	}

+bool Editor::WrapLines(enum wrapScope ws) {

 	int goodTopLine = topLine;

 	bool wrapOccurred = false;

-	if (wrapStart <= pdoc->LinesTotal()) {

-		if (wrapState == eWrapNone) {

-			if (wrapWidth != LineLayout::wrapWidthInfinite) {

-				wrapWidth = LineLayout::wrapWidthInfinite;

-				for (int lineDoc = 0; lineDoc < pdoc->LinesTotal(); lineDoc++) {

-					cs.SetHeight(lineDoc, 1 +

-						(vs.annotationVisible ? pdoc->AnnotationLines(lineDoc) : 0));

-				}

-				wrapOccurred = true;

+	if (wrapState == eWrapNone) {

+		if (wrapWidth != LineLayout::wrapWidthInfinite) {

+			wrapWidth = LineLayout::wrapWidthInfinite;

+			for (int lineDoc = 0; lineDoc < pdoc->LinesTotal(); lineDoc++) {

+				cs.SetHeight(lineDoc, 1 +

+					(vs.annotationVisible ? pdoc->AnnotationLines(lineDoc) : 0));

+			}

+			wrapOccurred = true;

+		}

+		wrapPending.Reset();

+

+	} else if (wrapPending.NeedsWrap()) {

+		wrapPending.start = std::min(wrapPending.start, pdoc->LinesTotal());

+		if (!SetIdle(true)) {

+			// Idle processing not supported so full wrap required.

+			ws = wsAll;

+		}

+		// Decide where to start wrapping

+		int lineToWrap = wrapPending.start;

+		int lineToWrapEnd = std::min(wrapPending.end, pdoc->LinesTotal());

+		const int lineDocTop = cs.DocFromDisplay(topLine);

+		const int subLineTop = topLine - cs.DisplayFromDoc(lineDocTop);

+		if (ws == wsVisible) {

+			lineToWrap = Platform::Clamp(lineDocTop-5, wrapPending.start, pdoc->LinesTotal());

+			// Priority wrap to just after visible area.

+			// Since wrapping could reduce display lines, treat each

+			// as taking only one display line.

+			lineToWrapEnd = lineDocTop;

+			int lines = LinesOnScreen() + 1;

+			while ((lineToWrapEnd < cs.LinesInDoc()) && (lines>0)) {

+				if (cs.GetVisible(lineToWrapEnd))

+					lines--;

+				lineToWrapEnd++;

+			}

+			// .. and if the paint window is outside pending wraps

+			if ((lineToWrap > wrapPending.end) || (lineToWrapEnd < wrapPending.start)) {

+				// Currently visible text does not need wrapping

+				return false;

 			}

-			wrapStart = wrapLineLarge;

-			wrapEnd = wrapLineLarge;

-		} else {

-			if (wrapEnd >= pdoc->LinesTotal())

-				wrapEnd = pdoc->LinesTotal();

-			//ElapsedTime et;

-			int lineDocTop = cs.DocFromDisplay(topLine);

-			int subLineTop = topLine - cs.DisplayFromDoc(lineDocTop);

+		} else if (ws == wsIdle) {

+			lineToWrapEnd = lineToWrap + LinesOnScreen() + 100;

+		}

+		const int lineEndNeedWrap = std::min(wrapPending.end, pdoc->LinesTotal());

+		lineToWrapEnd = std::min(lineToWrapEnd, lineEndNeedWrap);

+

+		// Ensure all lines being wrapped are styled.

+		pdoc->EnsureStyledTo(pdoc->LineStart(lineToWrapEnd));

+

+		if (lineToWrap < lineToWrapEnd) {

+

 			PRectangle rcTextArea = GetClientRectangle();

 			rcTextArea.left = vs.textStart;

-			rcTextArea.right -= vs.textStart;

+			rcTextArea.right -= vs.rightMarginWidth;

 			wrapWidth = rcTextArea.Width();

 			RefreshStyleData();

 			AutoSurface surface(this);

 			if (surface) {

-				bool priorityWrap = false;

-				int lastLineToWrap = wrapEnd;

-				int lineToWrap = wrapStart;

-				if (!fullWrap) {

-					if (priorityWrapLineStart >= 0) {

-						// This is a priority wrap.

-						lineToWrap = priorityWrapLineStart;

-						lastLineToWrap = priorityWrapLineStart + linesInOneCall;

-						priorityWrap = true;

-					} else {

-						// This is idle wrap.

-						lastLineToWrap = wrapStart + linesInOneCall;

-					}

-					if (lastLineToWrap >= wrapEnd)

-						lastLineToWrap = wrapEnd;

-				} // else do a fullWrap.

-

-				// Ensure all lines being wrapped are styled.

-				pdoc->EnsureStyledTo(pdoc->LineEnd(lastLineToWrap));

+//Platform::DebugPrintf("Wraplines: scope=%0d need=%0d..%0d perform=%0d..%0d\n", ws, wrapPending.start, wrapPending.end, lineToWrap, lineToWrapEnd);

 

-				// Platform::DebugPrintf("Wraplines: full = %d, priorityStart = %d (wrapping: %d to %d)\n", fullWrap, priorityWrapLineStart, lineToWrap, lastLineToWrap);

-				// Platform::DebugPrintf("Pending wraps: %d to %d\n", wrapStart, wrapEnd);

-				while (lineToWrap < lastLineToWrap) {

+				while (lineToWrap < lineToWrapEnd) {

 					if (WrapOneLine(surface, lineToWrap)) {

 						wrapOccurred = true;

 					}

+					wrapPending.Wrapped(lineToWrap);

 					lineToWrap++;

 				}

-				if (!priorityWrap)

-					wrapStart = lineToWrap;

-				// If wrapping is done, bring it to resting position

-				if (wrapStart >= wrapEnd) {

-					wrapStart = wrapLineLarge;

-					wrapEnd = wrapLineLarge;

-				}

+

+				goodTopLine = cs.DisplayFromDoc(lineDocTop) + std::min(subLineTop, cs.GetHeight(lineDocTop)-1);

 			}

-			goodTopLine = cs.DisplayFromDoc(lineDocTop);

-			if (subLineTop < cs.GetHeight(lineDocTop))

-				goodTopLine += subLineTop;

-			else

-				goodTopLine += cs.GetHeight(lineDocTop);

-			//double durWrap = et.Duration(true);

-			//Platform::DebugPrintf("Wrap:%9.6g \n", durWrap);

+		}

+

+		// If wrapping is done, bring it to resting position

+		if (wrapPending.start >= lineEndNeedWrap) {

+			wrapPending.Reset();

 		}

 	}

+

 	if (wrapOccurred) {

 		SetScrollBars();

 		SetTopLine(Platform::Clamp(goodTopLine, 0, MaxScrollPos()));

 		SetVerticalScrollPos();

 	}

+

 	return wrapOccurred;

 }

 

@@ -1833,6 +1808,8 @@ void Editor::PaintSelMargin(Surface *surfWindow, PRectangle &rc) {
 	if (vs.fixedColumnWidth == 0)

 		return;

 

+	AllocateGraphics();

+	RefreshStyleData();

 	RefreshPixMaps(surfWindow);

 

 	PRectangle rcMargin = GetClientRectangle();

@@ -3501,7 +3478,7 @@ void Editor::DrawCarets(Surface *surface, ViewStyle &vsDraw, int lineDoc, int xS
 					/* Dragging text, use a line caret */

 					rcCaret.left = xposCaret - caretWidthOffset;

 					rcCaret.right = rcCaret.left + vsDraw.caretWidth;

-				} else if (inOverstrike) {

+				} else if (inOverstrike && drawOverstrikeCaret) {

 					/* Overstrike (insert mode), use a modified bar caret */

 					rcCaret.top = rcCaret.bottom - 2;

 					rcCaret.left = xposCaret + 1;

@@ -3543,6 +3520,8 @@ void Editor::Paint(Surface *surfaceWindow, PRectangle rcArea) {
 		return;	// Scroll bars may have changed so need redraw

 	RefreshPixMaps(surfaceWindow);

 

+	paintAbandonedByStyling = false;

+

 	StyleToPositionInView(PositionAfterArea(rcArea));

 

 	PRectangle rcClient = GetClientRectangle();

@@ -3558,19 +3537,13 @@ void Editor::Paint(Surface *surfaceWindow, PRectangle rcArea) {
 		ypos += screenLinePaintFirst * vs.lineHeight;

 	int yposScreen = screenLinePaintFirst * vs.lineHeight;

 

-	bool paintAbandonedByStyling = paintState == paintAbandoned;

 	if (NotifyUpdateUI()) {

 		RefreshStyleData();

 		RefreshPixMaps(surfaceWindow);

 	}

 

-	// Call priority lines wrap on a window of lines which are likely

-	// to rendered with the following paint (that is wrap the visible

-	// 	lines first).

-	int startLineToWrap = cs.DocFromDisplay(topLine) - 5;

-	if (startLineToWrap < 0)

-		startLineToWrap = 0;

-	if (WrapLines(false, startLineToWrap)) {

+	// Wrap the visible lines if needed.

+	if (WrapLines(wsVisible)) {

 		// The wrapping process has changed the height of some lines so

 		// abandon this paint for a complete repaint.

 		if (AbandonPaint()) {

@@ -4742,6 +4715,8 @@ void Editor::NotifyModified(Document *, DocModification mh, void *) {
 			// Update contraction state for inserted and removed lines

 			// lineOfPos should be calculated in context of state before modification, shouldn't it

 			int lineOfPos = pdoc->LineFromPosition(mh.position);

+			if (mh.position > pdoc->LineStart(lineOfPos))

+				lineOfPos++;	// Affecting subsequent lines

 			if (mh.linesAdded > 0) {

 				cs.InsertLines(lineOfPos, mh.linesAdded);

 			} else {

@@ -5027,18 +5002,28 @@ void Editor::ChangeCaseOfSelection(int caseMapping) {
 				size_t firstDifference = 0;

 				while (sMapped[firstDifference] == sText[firstDifference])

 					firstDifference++;

-				size_t lastDifference = sMapped.size() - 1;

-				while (sMapped[lastDifference] == sText[lastDifference])

-					lastDifference--;

-				size_t endSame = sMapped.size() - 1 - lastDifference;

+				size_t lastDifferenceText = sText.size() - 1;

+				size_t lastDifferenceMapped = sMapped.size() - 1;

+				while (sMapped[lastDifferenceMapped] == sText[lastDifferenceText]) {

+					lastDifferenceText--;

+					lastDifferenceMapped--;

+				}

+				size_t endDifferenceText = sText.size() - 1 - lastDifferenceText;

 				pdoc->DeleteChars(

 					static_cast<int>(currentNoVS.Start().Position() + firstDifference),

-					static_cast<int>(rangeBytes - firstDifference - endSame));

+					static_cast<int>(rangeBytes - firstDifference - endDifferenceText));

 				pdoc->InsertString(

 					static_cast<int>(currentNoVS.Start().Position() + firstDifference),

 					sMapped.c_str() + firstDifference,

-					static_cast<int>(lastDifference - firstDifference + 1));

+					static_cast<int>(lastDifferenceMapped - firstDifference + 1));

 				// Automatic movement changes selection so reset to exactly the same as it was.

+				int diffSizes = static_cast<int>(sMapped.size() - sText.size());

+				if (diffSizes != 0) {

+					if (current.anchor > current.caret)

+						current.anchor.Add(diffSizes);

+					else

+						current.caret.Add(diffSizes);

+				}

 				sel.Range(r) = current;

 			}

 		}

@@ -6764,9 +6749,9 @@ bool Editor::Idle() {
 

 	if (!wrappingDone) {

 		// Wrap lines during idle.

-		WrapLines(false, -1);

+		WrapLines(wsIdle);

 		// No more wrapping

-		if (wrapStart == wrapEnd)

+		if (!wrapPending.NeedsWrap())

 			wrappingDone = true;

 	}

 

@@ -6867,6 +6852,7 @@ void Editor::CheckForChangeOutsidePaint(Range r) {
 

 		if (!PaintContains(rcRange)) {

 			AbandonPaint();

+			paintAbandonedByStyling = true;

 		}

 	}

 }

@@ -7069,8 +7055,8 @@ int Editor::ContractedFoldNext(int lineStart) const {
 void Editor::EnsureLineVisible(int lineDoc, bool enforcePolicy) {

 

 	// In case in need of wrapping to ensure DisplayFromDoc works.

-	if (lineDoc >= wrapStart)

-		WrapLines(true, -1);

+	if (lineDoc >= wrapPending.start)

+		WrapLines(wsAll);

 

 	if (!cs.GetVisible(lineDoc)) {

 		// Back up to find a non-blank line

diff --git a/scintilla/src/Editor.h b/scintilla/src/Editor.h
index 5cc70bf..cbd11f4 100644
--- a/scintilla/src/Editor.h
+++ b/scintilla/src/Editor.h
@@ -125,6 +125,41 @@ private:
 	}

 };

 

+struct WrapPending {

+	// The range of lines that need to be wrapped

+	enum { lineLarge = 0x7ffffff };

+	int start;	// When there are wraps pending, will be in document range

+	int end;	// May be lineLarge to indicate all of document after start

+	WrapPending() {

+		start = lineLarge;

+		end = lineLarge;

+	}

+	void Reset() {

+		start = lineLarge;

+		end = lineLarge;

+	}

+	void Wrapped(int line) {

+		if (start == line)

+			start++;

+	}

+	bool NeedsWrap() const {

+		return start < end;

+	}

+	bool AddRange(int lineStart, int lineEnd) {

+		const bool neededWrap = NeedsWrap();

+		bool changed = false;

+		if (start > lineStart) {

+			start = lineStart;

+			changed = true;

+		}

+		if ((end < lineEnd) || !neededWrap) {

+			end = lineEnd;

+			changed = true;

+		}

+		return changed;

+	}

+};

+

 /**

  */

 class Editor : public DocWatcher {

@@ -159,6 +194,7 @@ protected:	// ScintillaBase subclass needs access to much of Editor
 	bool hasFocus;

 	bool hideSelection;

 	bool inOverstrike;

+	bool drawOverstrikeCaret;

 	bool mouseDownCaptures;

 

 	/** In bufferedDraw mode, graphics operations are drawn to a pixmap and then copied to

@@ -238,6 +274,7 @@ protected:	// ScintillaBase subclass needs access to much of Editor
 	int theEdge;

 

 	enum { notPainting, painting, paintAbandoned } paintState;

+	bool paintAbandonedByStyling;

 	PRectangle rcPaint;

 	bool paintingAllText;

 	bool willRedrawAll;

@@ -272,10 +309,8 @@ protected:	// ScintillaBase subclass needs access to much of Editor
 

 	// Wrapping support

 	enum { eWrapNone, eWrapWord, eWrapChar } wrapState;

-	enum { wrapLineLarge = 0x7ffffff };

 	int wrapWidth;

-	int wrapStart;

-	int wrapEnd;

+	WrapPending wrapPending;

 	int wrapVisualFlags;

 	int wrapVisualFlagsLocation;

 	int wrapVisualStartIndent;

@@ -389,9 +424,10 @@ protected:	// ScintillaBase subclass needs access to much of Editor
 	void InvalidateCaret();

 	virtual void UpdateSystemCaret();

 

-	void NeedWrapping(int docLineStart = 0, int docLineEnd = wrapLineLarge);

+	void NeedWrapping(int docLineStart=0, int docLineEnd=WrapPending::lineLarge);

 	bool WrapOneLine(Surface *surface, int lineToWrap);

-	bool WrapLines(bool fullWrap, int priorityWrapLineStart);

+	enum wrapScope {wsAll, wsVisible, wsIdle};

+	bool WrapLines(enum wrapScope ws);

 	void LinesJoin();

 	void LinesSplit(int pixelWidth);

 

diff --git a/scintilla/src/PositionCache.cxx b/scintilla/src/PositionCache.cxx
index 116263a..cada960 100644
--- a/scintilla/src/PositionCache.cxx
+++ b/scintilla/src/PositionCache.cxx
@@ -32,6 +32,7 @@
 #include "CharClassify.h"

 #include "Decoration.h"

 #include "ILexer.h"

+#include "CaseFolder.h"

 #include "Document.h"

 #include "Selection.h"

 #include "PositionCache.h"

diff --git a/scintilla/src/ScintillaBase.cxx b/scintilla/src/ScintillaBase.cxx
index 1ab8240..10c9260 100644
--- a/scintilla/src/ScintillaBase.cxx
+++ b/scintilla/src/ScintillaBase.cxx
@@ -42,6 +42,7 @@
 #include "AutoComplete.h"

 #include "CharClassify.h"

 #include "Decoration.h"

+#include "CaseFolder.h"

 #include "Document.h"

 #include "Selection.h"

 #include "PositionCache.h"

diff --git a/scintilla/src/Selection.cxx b/scintilla/src/Selection.cxx
index a708a53..0f9fcf3 100644
--- a/scintilla/src/Selection.cxx
+++ b/scintilla/src/Selection.cxx
@@ -8,6 +8,7 @@
 #include <stdlib.h>

 

 #include <vector>

+#include <algorithm>

 

 #include "Platform.h"

 

diff --git a/scintilla/src/UnicodeFromUTF8.h b/scintilla/src/UnicodeFromUTF8.h
new file mode 100644
index 0000000..24517e8
--- /dev/null
+++ b/scintilla/src/UnicodeFromUTF8.h
@@ -0,0 +1,19 @@
+// Scintilla source code edit control
+/** @file UnicodeFromUTF8.h
+ ** Lexer infrastructure.
+ **/
+// Copyright 2013 by Neil Hodgson <neilh@scintilla.org>
+// This file is in the public domain.
+
+inline int UnicodeFromUTF8(const unsigned char *us) {
+	if (us[0] < 0xC2) {
+		return us[0];
+	} else if (us[0] < 0xE0) {
+		return ((us[0] & 0x1F) << 6) + (us[1] & 0x3F);
+	} else if (us[0] < 0xF0) {
+		return ((us[0] & 0xF) << 12) + ((us[1] & 0x3F) << 6) + (us[2] & 0x3F);
+	} else if (us[0] < 0xF5) {
+		return ((us[0] & 0x7) << 18) + ((us[1] & 0x3F) << 12) + ((us[2] & 0x3F) << 6) + (us[3] & 0x3F);
+	}
+	return us[0];
+}
diff --git a/scintilla/src/ViewStyle.cxx b/scintilla/src/ViewStyle.cxx
index 7661821..4b99771 100644
--- a/scintilla/src/ViewStyle.cxx
+++ b/scintilla/src/ViewStyle.cxx
@@ -40,6 +40,9 @@ FontNames::~FontNames() {
 }

 

 void FontNames::Clear() {

+	for (std::vector<char *>::const_iterator it=names.begin(); it != names.end(); ++it) {

+		delete []*it;

+	}

 	names.clear();

 }

 

@@ -395,11 +398,11 @@ void ViewStyle::CalcLargestMarkerHeight() {
 	for (int m = 0; m <= MARKER_MAX; ++m) {

 		switch (markers[m].markType) {

 		case SC_MARK_PIXMAP:

-			if (markers[m].pxpm->GetHeight() > largestMarkerHeight)

+			if (markers[m].pxpm && markers[m].pxpm->GetHeight() > largestMarkerHeight)

 				largestMarkerHeight = markers[m].pxpm->GetHeight();

 			break;

 		case SC_MARK_RGBAIMAGE:

-			if (markers[m].image->GetHeight() > largestMarkerHeight)

+			if (markers[m].image && markers[m].image->GetHeight() > largestMarkerHeight)

 				largestMarkerHeight = markers[m].image->GetHeight();

 			break;

 		}

diff --git a/scintilla/version.txt b/scintilla/version.txt
index 70f86c7..2d40575 100644
--- a/scintilla/version.txt
+++ b/scintilla/version.txt
@@ -1 +1 @@
-333

+334

diff --git a/scintilla/win32/PlatWin.cxx b/scintilla/win32/PlatWin.cxx
index 027f299..d9c65f8 100644
--- a/scintilla/win32/PlatWin.cxx
+++ b/scintilla/win32/PlatWin.cxx
@@ -1564,8 +1564,8 @@ void SurfaceD2D::DrawRGBAImage(PRectangle rc, int width, int height, const unsig
 		if (SUCCEEDED(hr)) {

 			D2D1_RECT_F rcDestination = {rc.left, rc.top, rc.right, rc.bottom};

 			pRenderTarget->DrawBitmap(bitmap, rcDestination);

+			bitmap->Release();

 		}

-		bitmap->Release();

 	}

 }

 

@@ -1669,8 +1669,8 @@ XYPOSITION SurfaceD2D::WidthText(Font &font_, const char *s, int len) {
 		HRESULT hr = pIDWriteFactory->CreateTextLayout(tbuf.buffer, tbuf.tlen, pTextFormat, 1000.0, 1000.0, &pTextLayout);

 		if (SUCCEEDED(hr)) {

 			DWRITE_TEXT_METRICS textMetrics;

-			pTextLayout->GetMetrics(&textMetrics);

-			width = textMetrics.widthIncludingTrailingWhitespace;

+			if (SUCCEEDED(pTextLayout->GetMetrics(&textMetrics)))

+				width = textMetrics.widthIncludingTrailingWhitespace;

 			pTextLayout->Release();

 		}

 	}

@@ -1694,7 +1694,8 @@ void SurfaceD2D::MeasureWidths(Font &font_, const char *s, int len, XYPOSITION *
 		if (!SUCCEEDED(hr))

 			return;

 		// For now, assuming WCHAR == cluster

-		pTextLayout->GetClusterMetrics(clusterMetrics, clusters, &count);

+		if (!SUCCEEDED(pTextLayout->GetClusterMetrics(clusterMetrics, clusters, &count)))

+			return;

 		FLOAT position = 0.0f;

 		size_t ti=0;

 		for (size_t ci=0;ci<count;ci++) {

@@ -1771,8 +1772,8 @@ XYPOSITION SurfaceD2D::WidthChar(Font &font_, char ch) {
 		HRESULT hr = pIDWriteFactory->CreateTextLayout(&wch, 1, pTextFormat, 1000.0, 1000.0, &pTextLayout);

 		if (SUCCEEDED(hr)) {

 			DWRITE_TEXT_METRICS textMetrics;

-			pTextLayout->GetMetrics(&textMetrics);

-			width = textMetrics.widthIncludingTrailingWhitespace;

+			if (SUCCEEDED(pTextLayout->GetMetrics(&textMetrics)))

+				width = textMetrics.widthIncludingTrailingWhitespace;

 			pTextLayout->Release();

 		}

 	}

@@ -1814,8 +1815,8 @@ XYPOSITION SurfaceD2D::AverageCharWidth(Font &font_) {
 			pTextFormat, 1000.0, 1000.0, &pTextLayout);

 		if (SUCCEEDED(hr)) {

 			DWRITE_TEXT_METRICS textMetrics;

-			pTextLayout->GetMetrics(&textMetrics);

-			width = textMetrics.width / wcslen(wszAllAlpha);

+			if (SUCCEEDED(pTextLayout->GetMetrics(&textMetrics)))

+				width = textMetrics.width / wcslen(wszAllAlpha);

 			pTextLayout->Release();

 		}

 	}

@@ -1887,7 +1888,12 @@ static RECT RectFromMonitor(HMONITOR hMonitor) {
 		}

 	}

 	RECT rc = {0, 0, 0, 0};

-	::SystemParametersInfoA(SPI_GETWORKAREA, 0, &rc, 0);

+	if (::SystemParametersInfoA(SPI_GETWORKAREA, 0, &rc, 0) == 0) {

+		rc.left = 0;

+		rc.top = 0;

+		rc.right = 0;

+		rc.bottom = 0;

+	}

 	return rc;

 }

 

@@ -2133,7 +2139,7 @@ class ListBoxX : public ListBox {
 

 	HWND GetHWND() const;

 	void AppendListItem(const char *text, const char *numword);

-	void AdjustWindowRect(PRectangle *rc) const;

+	static void AdjustWindowRect(PRectangle *rc);

 	int ItemHeight() const;

 	int MinClientWidth() const;

 	int TextOffset() const;

@@ -2496,7 +2502,7 @@ void ListBoxX::SetList(const char *list, char separator, char typesep) {
 	SetRedraw(true);

 }

 

-void ListBoxX::AdjustWindowRect(PRectangle *rc) const {

+void ListBoxX::AdjustWindowRect(PRectangle *rc) {

 	RECT rcw = RectFromPRectangle(*rc);

 	::AdjustWindowRectEx(&rcw, WS_THICKFRAME, false, WS_EX_WINDOWEDGE);

 	*rc = PRectangle(rcw.left, rcw.top, rcw.right, rcw.bottom);

@@ -3202,6 +3208,12 @@ int Platform::Clamp(int val, int minVal, int maxVal) {
 	return val;

 }

 

+#ifdef _MSC_VER

+// GetVersionEx has been deprecated fro Windows 8.1 but called here to determine if Windows 9x.

+// Too dangerous to find alternate check.

+#pragma warning(disable: 4996)

+#endif

+

 void Platform_Initialise(void *hInstance) {

 	OSVERSIONINFO osv = {sizeof(OSVERSIONINFO),0,0,0,0,TEXT("")};

 	::GetVersionEx(&osv);

@@ -3228,6 +3240,10 @@ void Platform_Initialise(void *hInstance) {
 	ListBoxX_Register();

 }

 

+#ifdef _MSC_VER

+#pragma warning(default: 4996)

+#endif

+

 void Platform_Finalise() {

 	if (reverseArrowCursor != NULL)

 		::DestroyCursor(reverseArrowCursor);

diff --git a/scintilla/win32/ScintillaWin.cxx b/scintilla/win32/ScintillaWin.cxx
index d6e879e..8b3a98f 100644
--- a/scintilla/win32/ScintillaWin.cxx
+++ b/scintilla/win32/ScintillaWin.cxx
@@ -60,12 +60,15 @@
 #include "ViewStyle.h"

 #include "CharClassify.h"

 #include "Decoration.h"

+#include "CaseFolder.h"

 #include "Document.h"

 #include "Selection.h"

 #include "PositionCache.h"

 #include "Editor.h"

 #include "ScintillaBase.h"

 #include "UniConversion.h"

+#include "CaseConvert.h"

+

 #include "PlatWin.h"

 

 #ifdef SCI_LEXER

@@ -89,9 +92,7 @@
 #endif

 

 #include <commctrl.h>

-#ifndef __DMC__

 #include <zmouse.h>

-#endif

 #include <ole2.h>

 

 #ifndef MK_ALT

@@ -217,8 +218,10 @@ class ScintillaWin :
 

 	virtual void Initialise();

 	virtual void Finalise();

+#if defined(USE_D2D)

 	void EnsureRenderTarget();

 	void DropRenderTarget();

+#endif

 	HWND MainHWND();

 

 	static sptr_t DirectFunction(

@@ -404,15 +407,18 @@ void ScintillaWin::Finalise() {
 	ScintillaBase::Finalise();

 	SetTicking(false);

 	SetIdle(false);

+#if defined(USE_D2D)

 	DropRenderTarget();

+#endif

 	::RevokeDragDrop(MainHWND());

 	if (SUCCEEDED(hrOle)) {

 		::OleUninitialize();

 	}

 }

 

-void ScintillaWin::EnsureRenderTarget() {

 #if defined(USE_D2D)

+

+void ScintillaWin::EnsureRenderTarget() {

 	if (!renderTargetValid) {

 		DropRenderTarget();

 		renderTargetValid = true;

@@ -454,18 +460,17 @@ void ScintillaWin::EnsureRenderTarget() {
 		// need to be recreated.

 		DropGraphics(false);

 	}

-#endif

 }

 

 void ScintillaWin::DropRenderTarget() {

-#if defined(USE_D2D)

 	if (pRenderTarget) {

 		pRenderTarget->Release();

 		pRenderTarget = 0;

 	}

-#endif

 }

 

+#endif

+

 HWND ScintillaWin::MainHWND() {

 	return reinterpret_cast<HWND>(wMain.GetID());

 }

@@ -630,10 +635,6 @@ LRESULT ScintillaWin::WndPaint(uptr_t wParam) {
 }

 

 sptr_t ScintillaWin::HandleComposition(uptr_t wParam, sptr_t lParam) {

-#ifdef __DMC__

-	// Digital Mars compiler does not include Imm library

-	return 0;

-#else

 	if (lParam & GCS_RESULTSTR) {

 		HIMC hIMC = ::ImmGetContext(MainHWND());

 		if (hIMC) {

@@ -668,7 +669,6 @@ sptr_t ScintillaWin::HandleComposition(uptr_t wParam, sptr_t lParam) {
 		return 0;

 	}

 	return ::DefWindowProc(MainHWND(), WM_IME_COMPOSITION, wParam, lParam);

-#endif

 }

 

 // Translate message IDs from WM_* and EM_* to SCI_* so can partly emulate Windows Edit control

@@ -871,13 +871,10 @@ sptr_t ScintillaWin::WndProc(unsigned int iMessage, uptr_t wParam, sptr_t lParam
 			return ::DefWindowProc(MainHWND(), iMessage, wParam, lParam);

 

 		case WM_LBUTTONDOWN: {

-#ifndef __DMC__

-			// Digital Mars compiler does not include Imm library

 			// For IME, set the composition string as the result string.

 			HIMC hIMC = ::ImmGetContext(MainHWND());

 			::ImmNotifyIME(hIMC, NI_COMPOSITIONSTR, CPS_COMPLETE, 0);

 			::ImmReleaseContext(MainHWND(), hIMC);

-#endif

 			//

 			//Platform::DebugPrintf("Buttdown %d %x %x %x %x %x\n",iMessage, wParam, lParam,

 			//	Platform::IsKeyDown(VK_SHIFT),

@@ -1449,55 +1446,6 @@ void ScintillaWin::NotifyDoubleClick(Point pt, bool shift, bool ctrl, bool alt)
 			  MAKELPARAM(pt.x, pt.y));

 }

 

-class CaseFolderUTF8 : public CaseFolderTable {

-	// Allocate the expandable storage here so that it does not need to be reallocated

-	// for each call to Fold.

-	std::vector<wchar_t> utf16Mixed;

-	std::vector<wchar_t> utf16Folded;

-public:

-	CaseFolderUTF8() {

-		StandardASCII();

-	}

-	virtual size_t Fold(char *folded, size_t sizeFolded, const char *mixed, size_t lenMixed) {

-		if ((lenMixed == 1) && (sizeFolded > 0)) {

-			folded[0] = mapping[static_cast<unsigned char>(mixed[0])];

-			return 1;

-		} else {

-			if (lenMixed > utf16Mixed.size()) {

-				utf16Mixed.resize(lenMixed + 8);

-			}

-			size_t nUtf16Mixed = ::MultiByteToWideChar(65001, 0, mixed,

-				static_cast<int>(lenMixed),

-				&utf16Mixed[0],

-				static_cast<int>(utf16Mixed.size()));

-

-			if (nUtf16Mixed == 0) {

-				// Failed to convert -> bad UTF-8

-				folded[0] = '\0';

-				return 1;

-			}

-

-			if (nUtf16Mixed * 4 > utf16Folded.size()) {	// Maximum folding expansion factor of 4

-				utf16Folded.resize(nUtf16Mixed * 4 + 8);

-			}

-			int lenFlat = ::LCMapStringW(LOCALE_SYSTEM_DEFAULT,

-				LCMAP_LINGUISTIC_CASING | LCMAP_LOWERCASE,

-				&utf16Mixed[0],

-				static_cast<int>(nUtf16Mixed),

-				&utf16Folded[0],

-				static_cast<int>(utf16Folded.size()));

-

-			size_t lenOut = UTF8Length(&utf16Folded[0], lenFlat);

-			if (lenOut < sizeFolded) {

-				UTF8FromUTF16(&utf16Folded[0], lenFlat, folded, static_cast<int>(lenOut));

-				return lenOut;

-			} else {

-				return 0;

-			}

-		}

-	}

-};

-

 class CaseFolderDBCS : public CaseFolderTable {

 	// Allocate the expandable storage here so that it does not need to be reallocated

 	// for each call to Fold.

@@ -1527,15 +1475,23 @@ public:
 				return 1;

 			}

 

-			if (nUtf16Mixed * 4 > utf16Folded.size()) {	// Maximum folding expansion factor of 4

-				utf16Folded.resize(nUtf16Mixed * 4 + 8);

+			unsigned int lenFlat = 0;

+			for (size_t mixIndex=0; mixIndex < nUtf16Mixed; mixIndex++) {

+				if ((lenFlat + 20) > utf16Folded.size())

+					utf16Folded.resize(lenFlat + 60);

+				const char *foldedUTF8 = CaseConvert(utf16Mixed[mixIndex], CaseConversionFold);

+				if (foldedUTF8) {

+					// Maximum length of a case conversion is 6 bytes, 3 characters

+					wchar_t wFolded[20];

+					unsigned int charsConverted = UTF16FromUTF8(foldedUTF8,

+							static_cast<unsigned int>(strlen(foldedUTF8)), 

+							wFolded, sizeof(wFolded)/sizeof(wFolded[0]));

+					for (size_t j=0;j<charsConverted;j++)

+						utf16Folded[lenFlat++] = wFolded[j];

+				} else {

+					utf16Folded[lenFlat++] = utf16Mixed[mixIndex];

+				}

 			}

-			int lenFlat = ::LCMapStringW(LOCALE_SYSTEM_DEFAULT,

-				LCMAP_LINGUISTIC_CASING | LCMAP_LOWERCASE,

-				&utf16Mixed[0],

-				static_cast<int>(nUtf16Mixed),

-				&utf16Folded[0],

-				static_cast<int>(utf16Folded.size()));

 

 			size_t lenOut = ::WideCharToMultiByte(cp, 0,

 				&utf16Folded[0], lenFlat,

@@ -1556,7 +1512,7 @@ public:
 CaseFolder *ScintillaWin::CaseFolderForEncoding() {

 	UINT cpDest = CodePageOfDocument();

 	if (cpDest == SC_CP_UTF8) {

-		return new CaseFolderUTF8();

+		return new CaseFolderUnicode();

 	} else {

 		if (pdoc->dbcsCodePage == 0) {

 			CaseFolderTable *pcf = new CaseFolderTable();

@@ -1570,16 +1526,21 @@ CaseFolder *ScintillaWin::CaseFolderForEncoding() {
 				unsigned int lengthUTF16 = ::MultiByteToWideChar(cpDoc, 0, sCharacter, 1,

 					wCharacter, sizeof(wCharacter)/sizeof(wCharacter[0]));

 				if (lengthUTF16 == 1) {

-					wchar_t wLower[20];

-					int charsConverted = ::LCMapStringW(LOCALE_SYSTEM_DEFAULT,

-						LCMAP_LINGUISTIC_CASING | LCMAP_LOWERCASE,

-						wCharacter, lengthUTF16, wLower, sizeof(wLower)/sizeof(wLower[0]));

-					char sCharacterLowered[20];

-					unsigned int lengthConverted = ::WideCharToMultiByte(cpDoc, 0,

-						wLower, charsConverted,

-						sCharacterLowered, sizeof(sCharacterLowered), NULL, 0);

-					if ((lengthConverted == 1) && (sCharacter[0] != sCharacterLowered[0])) {

-						pcf->SetTranslation(sCharacter[0], sCharacterLowered[0]);

+					const char *caseFolded = CaseConvert(wCharacter[0], CaseConversionFold);

+					if (caseFolded) {

+						wchar_t wLower[20];

+						unsigned int charsConverted = UTF16FromUTF8(caseFolded,

+							static_cast<unsigned int>(strlen(caseFolded)), 

+							wLower, sizeof(wLower)/sizeof(wLower[0]));

+						if (charsConverted == 1) {

+							char sCharacterLowered[20];

+							unsigned int lengthConverted = ::WideCharToMultiByte(cpDoc, 0,

+								wLower, charsConverted,

+								sCharacterLowered, sizeof(sCharacterLowered), NULL, 0);

+							if ((lengthConverted == 1) && (sCharacter[0] != sCharacterLowered[0])) {

+								pcf->SetTranslation(sCharacter[0], sCharacterLowered[0]);

+							}

+						}

 					}

 				}

 			}

@@ -1591,13 +1552,17 @@ CaseFolder *ScintillaWin::CaseFolderForEncoding() {
 }

 

 std::string ScintillaWin::CaseMapString(const std::string &s, int caseMapping) {

-	if (s.size() == 0)

-		return std::string();

-

-	if (caseMapping == cmSame)

+	if ((s.size() == 0) || (caseMapping == cmSame))

 		return s;

 

 	UINT cpDoc = CodePageOfDocument();

+	if (cpDoc == SC_CP_UTF8) {

+		std::string retMapped(s.length() * maxExpansionCaseConversion, 0);

+		size_t lenMapped = CaseConvertString(&retMapped[0], retMapped.length(), s.c_str(), s.length(), 

+			(caseMapping == cmUpper) ? CaseConversionUpper : CaseConversionLower);

+		retMapped.resize(lenMapped);

+		return retMapped;

+	}

 

 	unsigned int lengthUTF16 = ::MultiByteToWideChar(cpDoc, 0, s.c_str(),

 		static_cast<int>(s.size()), NULL, 0);

@@ -1607,63 +1572,27 @@ std::string ScintillaWin::CaseMapString(const std::string &s, int caseMapping) {
 	DWORD mapFlags = LCMAP_LINGUISTIC_CASING |

 		((caseMapping == cmUpper) ? LCMAP_UPPERCASE : LCMAP_LOWERCASE);

 

-	// Many conversions performed by search function are short so optimize this case.

-	enum { shortSize=20 };

-

-	if (s.size() > shortSize) {

-		// Use dynamic allocations for long strings

-

-		// Change text to UTF-16

-		std::vector<wchar_t> vwcText(lengthUTF16);

-		::MultiByteToWideChar(cpDoc, 0, s.c_str(), static_cast<int>(s.size()), &vwcText[0], lengthUTF16);

-

-		// Change case

-		int charsConverted = ::LCMapStringW(LOCALE_SYSTEM_DEFAULT, mapFlags,

-			&vwcText[0], lengthUTF16, NULL, 0);

-		std::vector<wchar_t> vwcConverted(charsConverted);

-		::LCMapStringW(LOCALE_SYSTEM_DEFAULT, mapFlags,

-			&vwcText[0], lengthUTF16, &vwcConverted[0], charsConverted);

+	// Change text to UTF-16

+	std::vector<wchar_t> vwcText(lengthUTF16);

+	::MultiByteToWideChar(cpDoc, 0, s.c_str(), static_cast<int>(s.size()), &vwcText[0], lengthUTF16);

 

-		// Change back to document encoding

-		unsigned int lengthConverted = ::WideCharToMultiByte(cpDoc, 0,

-			&vwcConverted[0], static_cast<int>(vwcConverted.size()),

-			NULL, 0, NULL, 0);

-		std::vector<char> vcConverted(lengthConverted);

-		::WideCharToMultiByte(cpDoc, 0,

-			&vwcConverted[0], static_cast<int>(vwcConverted.size()),

-			&vcConverted[0], static_cast<int>(vcConverted.size()), NULL, 0);

+	// Change case

+	int charsConverted = ::LCMapStringW(LOCALE_SYSTEM_DEFAULT, mapFlags,

+		&vwcText[0], lengthUTF16, NULL, 0);

+	std::vector<wchar_t> vwcConverted(charsConverted);

+	::LCMapStringW(LOCALE_SYSTEM_DEFAULT, mapFlags,

+		&vwcText[0], lengthUTF16, &vwcConverted[0], charsConverted);

 

-		return std::string(&vcConverted[0], vcConverted.size());

+	// Change back to document encoding

+	unsigned int lengthConverted = ::WideCharToMultiByte(cpDoc, 0,

+		&vwcConverted[0], static_cast<int>(vwcConverted.size()),

+		NULL, 0, NULL, 0);

+	std::vector<char> vcConverted(lengthConverted);

+	::WideCharToMultiByte(cpDoc, 0,

+		&vwcConverted[0], static_cast<int>(vwcConverted.size()),

+		&vcConverted[0], static_cast<int>(vcConverted.size()), NULL, 0);

 

-	} else {

-		// Use static allocations for short strings as much faster

-		// A factor of 15 for single character strings

-

-		// Change text to UTF-16

-		wchar_t vwcText[shortSize];

-		::MultiByteToWideChar(cpDoc, 0, s.c_str(), static_cast<int>(s.size()),

-			vwcText, lengthUTF16);

-

-		// Change case

-		int charsConverted = ::LCMapStringW(LOCALE_SYSTEM_DEFAULT, mapFlags,

-			vwcText, lengthUTF16, NULL, 0);

-		// Full mapping may produce up to 3 characters per input character

-		wchar_t vwcConverted[shortSize*3];

-		::LCMapStringW(LOCALE_SYSTEM_DEFAULT, mapFlags, vwcText, lengthUTF16,

-			vwcConverted, charsConverted);

-

-		// Change back to document encoding

-		unsigned int lengthConverted = ::WideCharToMultiByte(cpDoc, 0,

-			vwcConverted, charsConverted,

-			NULL, 0, NULL, 0);

-		// Each UTF-16 code unit may need up to 3 bytes in UTF-8

-		char vcConverted[shortSize * 3 * 3];

-		::WideCharToMultiByte(cpDoc, 0,

-			vwcConverted, charsConverted,

-			vcConverted, lengthConverted, NULL, 0);

-

-		return std::string(vcConverted, lengthConverted);

-	}

+	return std::string(&vcConverted[0], vcConverted.size());

 }

 

 void ScintillaWin::Copy() {

@@ -2172,8 +2101,6 @@ DropTarget::DropTarget() {
  * Called when IME Window opened.

  */

 void ScintillaWin::ImeStartComposition() {

-#ifndef __DMC__

-	// Digital Mars compiler does not include Imm library

 	if (caret.active) {

 		// Move IME Window to current caret position

 		HIMC hIMC = ::ImmGetContext(MainHWND());

@@ -2214,7 +2141,6 @@ void ScintillaWin::ImeStartComposition() {
 		// Caret is displayed in IME window. So, caret in Scintilla is useless.

 		DropCaret();

 	}

-#endif

 }

 

 /** Called when IME Window closed. */

@@ -2613,7 +2539,7 @@ STDMETHODIMP ScintillaWin::Drop(LPDATAOBJECT pIDataSource, DWORD grfKeyState,
 			data.assign(convertedText.c_str(), convertedText.c_str()+convertedText.length()+1);

 		}

 

-		if (data.empty()) {

+		if (!SUCCEEDED(hr) || data.empty()) {

 			//Platform::DebugPrintf("Bad data format: 0x%x\n", hres);

 			return hr;

 		}

@@ -2832,7 +2758,12 @@ sptr_t PASCAL ScintillaWin::CTWndProc(
 						drtp.usage = D2D1_RENDER_TARGET_USAGE_NONE;

 						drtp.minLevel = D2D1_FEATURE_LEVEL_DEFAULT;

 

-						pD2DFactory->CreateHwndRenderTarget(drtp, dhrtp, &pCTRenderTarget);

+						if (!SUCCEEDED(pD2DFactory->CreateHwndRenderTarget(drtp, dhrtp, &pCTRenderTarget))) {

+							surfaceWindow->Release();

+							delete surfaceWindow;

+							::EndPaint(hWnd, &ps);

+							return 0;

+						}

 						surfaceWindow->Init(pCTRenderTarget, hWnd);

 						pCTRenderTarget->BeginDraw();

 #endif